CN107293306A - A kind of appraisal procedure of the Objective speech quality based on output - Google Patents
A kind of appraisal procedure of the Objective speech quality based on output Download PDFInfo
- Publication number
- CN107293306A CN107293306A CN201710475912.8A CN201710475912A CN107293306A CN 107293306 A CN107293306 A CN 107293306A CN 201710475912 A CN201710475912 A CN 201710475912A CN 107293306 A CN107293306 A CN 107293306A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- munderover
- sequence
- mfrac
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000013507 mapping Methods 0.000 claims abstract description 24
- 238000011156 evaluation Methods 0.000 claims abstract description 14
- 238000004364 calculation method Methods 0.000 claims abstract description 10
- 238000012544 monitoring process Methods 0.000 claims description 67
- 230000014509 gene expression Effects 0.000 claims description 60
- 230000006870 function Effects 0.000 claims description 33
- 230000001360 synchronised effect Effects 0.000 claims description 27
- 230000008569 process Effects 0.000 claims description 21
- 238000001914 filtration Methods 0.000 claims description 11
- 239000000203 mixture Substances 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 7
- 238000003780 insertion Methods 0.000 claims description 7
- 230000037431 insertion Effects 0.000 claims description 7
- 238000001228 spectrum Methods 0.000 claims description 7
- 230000000739 chaotic effect Effects 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000013139 quantization Methods 0.000 claims description 6
- 238000009432 framing Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 229910002056 binary alloy Inorganic materials 0.000 claims description 3
- 238000000205 computational method Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000002592 echocardiography Methods 0.000 claims description 3
- 230000000977 initiatory effect Effects 0.000 claims description 3
- 238000000611 regression analysis Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 238000001303 quality assessment method Methods 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000013441 quality evaluation Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008570 general process Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000013432 robust analysis Methods 0.000 description 1
- 230000005654 stationary process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/24—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being the cepstrum
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/60—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for measuring the quality of voice signals
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Complex Calculations (AREA)
- Other Investigation Or Analysis Of Materials By Electrical Means (AREA)
Abstract
The present invention provides a kind of method of the objective speech quality assessment based on output, comprises the following steps:Calculate the mel-frequency cepstrum coefficient of the distorted speech after system is transmitted;Obtain the reference model for meeting human hearing characteristic;The mel-frequency cepstrum coefficient of distorted speech and the reference model for meeting human hearing characteristic are subjected to uniformity measure calculation;One section of sequence is inserted in raw tone, the bit error rate that the sequence is extracted in the distorted speech after being transmitted by system is calculated;Measured according to uniformity and mapping relations that the bit error rate is set up between subjective MOS and homogeneity measure, obtain the objective forecast model to voice MOS to be evaluated points, pass through the objective evaluation that the objective forecast model carries out voice quality.Using the method for the present invention, step is simplified, easy to use, and is capable of the quality of effectively objective evaluation voice, independent of subjective assessment.
Description
Technical field
The present invention relates to voice process technology field, especially, it is related to a kind of Objective speech quality based on output
Appraisal procedure.
Background technology
Speech quality objective assessment refer to use machine automatic discrimination voice quality, by whether need to use input voice angle
Degree can be divided into two classes:Objective evaluation based on input-output mode and the objective evaluation based on the way of output.
In many fields, such as wireless mobile communications, space flight navigation and modern military often require that evaluation method has
Higher flexibility, real-time and versatility, and also will can be to voice matter in the case of it cannot get original input speech signal
Amount is estimated, and is difficult often to obtain corresponding raw tone, phonetic storage in the objective evaluation of the mode based on input-output
In terms of cost it is bigger, the drawbacks of existing certain under these application scenarios.
The general process of objective speech quality assessment method based on output is certain characteristic parameter of Calculation Estimation voice,
And uniformity calculating is carried out with learning the characteristic parameter of reference voice after concluding by particular model, final mapping obtains subjectivity
MOS points of estimate.In this process, the selection of characteristic parameter, training pattern and MOS points of mapping methods is most important
, it affects the performance of assessment system.Because human ear meets Bark critical band to the perception characteristic of sound, therefore in feature
Need to realize linear frequency and inflection frequency conversion during parameter extraction.Meanwhile, in this kind of application of radio communication, except from voice
Itself analyze outer, in addition it is also necessary to consider influence of the external factors such as channel quality to voice quality.
Therefore, a kind of appraisal procedure tool for the voice quality that can be used for after objective evaluation coding or channel transmission is designed
It is significant.
The content of the invention
It is an object of the invention to provide a kind of method of the objective speech quality assessment based on output.In view of human ear pair
The auditory properties of frequency, while the cepstral analysis of voice signal is taken into account, using mel-frequency cepstrum coefficient (Mel-Frequency
Cepstral Coefficients, MFCC) description phonetic feature.Trained by combining mel-frequency cepstrum coefficient and GMM-HMM
Model obtains speech objective distortion value, at the same by channel effect by error rate index be introduced into it is objective estimate, then set up master
See MOS point and it is objective estimate between mapping relations, the forecast model to subjective MOS is obtained, so as to be commented for objective
Voice quality after valency coding or channel transmission.Details as Follows:
A kind of appraisal procedure of the Objective speech quality based on output, comprises the following steps:
Calculate the mel-frequency cepstrum coefficient of the distorted speech after system is transmitted;Acquisition meets human hearing characteristic
Reference model;
The mel-frequency cepstrum coefficient of distorted speech and the reference model for meeting human hearing characteristic are subjected to uniformity amount
Degree is calculated;One section of sequence is inserted in raw tone, calculating extracts the sequence in the distorted speech after being transmitted by system
The bit error rate of row;
Measured and mapping relations that the bit error rate is set up between subjective MOS and homogeneity measure, obtained pair according to uniformity
Voice MOS to be evaluated points of objective forecast model, the objective evaluation of voice quality is carried out by the objective forecast model.
Preferred in above technical scheme, the calculating process of the mel-frequency cepstrum coefficient includes pretreatment, FFT and become
Change, four steps of Mel frequency filterings and discrete cosine transform.
Preferred in above technical scheme, the pretreatment specifically includes following steps:
Step 1.1, preemphasis, be specifically:Come using the digital filter of the lifting high frequency characteristics with 6dB/ octaves
Preemphasis is realized, its transmission function is expression formula 1):
H (z)=1- μ z-11);
Wherein:μ is pre emphasis factor, and its value is 0.9-1.0;
Step 1.2, end-point detection, be specifically:Carried out by setting the thresholding of short-time energy and short-time zero-crossing rate, if certain
The Short Time Speech signal that individual length is N is x (m), its short-time energy E expression formulas 2) calculate:
Its short-time zero-crossing rate Z expression formulas 3) calculate:
Wherein, sgn [] is sign function, i.e.,:
Step 1.3, framing and adding window, be specifically:The framing is that voice is divided into frame one by one, the length of each frame
For 10-30ms;The adding window is to carry out adding window to each frame signal using Hamming windows.
Preferred in above technical scheme, the detailed process of the adding window is:If frame signal is x (n), window function is w
(n), then signal y (n) after adding window is expression formula 4):
Y (n)=x (n) w (n), 0≤n≤N-1 4);
Wherein, N is the number of sampling per frame, and w (n) expression formula is w (n)=0.54-0.46cos [2 π n/ (N-1)], 0≤n≤
N-1。
Preferred in above technical scheme, the Mel frequency filterings are specifically:The discrete spectrum handled by FFT is used
Sequence triangular filter is filtered processing, obtains one group of Coefficient ml、m2、……;The number p of the wave filter group is cut by signal
Only frequency is determined, all wave filters generally cover from 0Hz to Nyquist 1/2nd of frequency, i.e. sample rate;miBy expressing
Formula 5) calculate obtain:
Wherein:
F [i] is triangle filtering
The centre frequency of device, meets:Mel (f [i+1])-Mel (f [i])=Mel (f [i])-Mel (f [i-1]);X (k) is frame signal x
(n) discrete spectrum after being handled through FFT.
Preferred in above technical scheme, the discrete cosine transform is specifically:By the Mel frequencies by Mel frequency filterings
Spectral transformation obtains Mel frequency cepstral coefficients, it is by expression formula 6 to time domain) calculate obtain:
Wherein:MFCC (i) is Mel frequency cepstral coefficients, and N is points per frame sample, and P is the number of wave filter group.
It is preferred in above technical scheme, obtain meet human hearing characteristic reference model detailed process it is as follows:
If the characteristic vector sequence of observation is O=o1,o2,…,oT, the state model sequence of the sequence is S=s1,s2,…,
sN, then the HMM model of the sequence be expressed as expression formula 7):
λ=(π, A, B) is 7);
Wherein, π={ πi=P (s1=i), i=1,2 ..., N } it is initial state probabilities vector;A={ aijFor between state
The transition probability matrix redirected, aijTo jump to state j probability from state i;B={ bi(ot)=P (ot|st=i), 2≤i≤
N-1 } collect for the output probability distribution of state;
To continuous HMM model, observation sequence is continuous signal, and its signal space corresponding with state j is with M mixed Gaussian
Density function and represent, such as expression formula 8) and expression formula 9) under:
Wherein, cjkThe coefficient of expression state j k-th of Gaussian Mixture Model Probability Density Function;μjkIt is the average of Gaussian density function
Vector;CjkFor covariance matrix, D is observation sequence O dimension;HMM parameters are by observation sequence O=o1,o2,…,oTEstimate
Arrive, the target of estimation is that the likelihood function P (O | λ) for making model and training data maximizes to estimate newest λ, even if
The likelihood function p (O | λ) forward direction probability calculation formula such as expression formula 10):
Wherein:α1(i)=π bi(o1),1≤i≤N;
The likelihood function p (O | λ) backward probability calculation formula such as expression formula 11):
Wherein:βT(i)=1,1≤i≤N;
To giving observation sequence O=o1,o2,…,oTNewest λ is obtained by revaluation, ξ is defined hereintWhen (i, j) is t
Quarter state be siAnd t+1 moment state is sjProbability, by expression formula 12) obtain:
Under conditions of setting models λ and observation sequence O, state siIt is expression formula 13 in moment t posterior probability):
Thus, the revaluation of HMM parameter lambdas is as follows:
In the parameter c of t state k-th of Gaussian mixture components of jjk, μjkAnd CjkBy expression formula 14), 15) and 16) weight
New estimation:
Wherein, γt(j, k) represents the probability in t state k-th of Gaussian mixture components of j, can be obtained by following formula:
Preferred in above technical scheme, the computational methods that uniformity is measured are specifically:Using expression formula 17) counted
Calculate:
Wherein:X1,...,XNIt is the mel-frequency cepstrum coefficient vector of distorted speech, N is vectorial number, and C is distorted speech
Measured with the uniformity of model.
Preferred in above technical scheme, the calculating process of the bit error rate is as follows:
Step A, one PN sequence of generation, and be multiplied with a chaos sequence, the generation of chaos sequence is reflected by logistic
Generation is penetrated, logistic mapping definitions are as follows:
xk+1=μ xk(1-xk)
Wherein, 0≤μ≤4 are referred to as branch parameter, xk∈ (0,1), when 3.5699456 ...<During μ≤4, logistic mappings
Work in the sequence { x that chaos state, i.e. primary condition are produced under logistic mappingsk;K=0,1,2,3 ... } it is aperiodic
, it is not convergent and very sensitive to initial value;Generate comprising the following steps that for monitoring data sequent:
Step a1, produce real-valued sequence first, and it is big for monitoring data sequent to choose the length that the position of some in sequence starts
Small one section;
Step a2, real-valued sequence is changed into binary sequence:By defining a threshold value Γ, obtained by real-valued sequence:
Binary chaotic sequence is { Γ (xk);K=0,1,2,3 ... };
Step a3, binary chaotic sequence is multiplied with a PN sequence, you can obtain monitoring data sequent;
Step B, for monitoring data sequent insert synchronous code, monitoring data sequent embedded below is extracted frame by frame;
Step C, the monitoring data sequent of synchronous code will be inserted in wavelet field in embedded voice signal, detailed process is as follows:
Step c1, selection Daubechies10 small echos are used as wavelet function;
Step c2, sub-frame processing is carried out to voice signal, the size per frame is 1152 sampled points, and every frame signal is entered
3 layers of wavelet transformation of row;
Step c3, wavelet coefficient is quantified, and monitoring data sequent is modulated, so that monitoring data sequent is embedded in into voice
In signal, if coefficient to be quantified is f, the bit of embedded monitoring data sequent is w, and quantization step is Δ, and monitoring sequence is contained after quantization
The coefficient of column information concretely comprises the following steps for f':
To f modulus and floor operation, as f > 0, ifN=m%2, then:
As f < 0, ifN=m%2, n=w, then:
Monitoring data sequent is embedded into voice signal one by one according to above-mentioned formula;
Step c4, the signal of embedded monitoring data sequent switched back into time-domain signal;
Embedded monitoring data sequent is extracted in step D, the voice received, and calculates the bit error rate, the process specifically extracted
Comprise the following steps:
Step d1, synchronous code is searched in voice signal, be specifically:If needing the length that the signal length searched for is L, then L
Degree should be more than the length of two synchronous codes and the summation of a complete monitoring data sequent length;If the initiating searches point of signal is
I=1, if the sample value of signalIn the range of 900-1100, then it is assumed that searched possible synchronous code,
It is compared using default synchronous code;If determined as synchronous code, then I points are the original position of monitoring data sequent, otherwise make I
=I+L;
Step d2, since the starting point found, to voice signal carry out wavelet transform;
Step d3, the operation for making contrary during with insertion to the coefficient f after wavelet decomposition, i.e.,:During f > 0, if
W=m%2;During f < 0, ifW=m%2;
So as to extract binary system monitoring data sequent;
Step d4, compare the monitoring data sequent extracted and the monitoring data sequent of insertion, by expression formula 18) calculate the bit error rate:
Wherein Seqsend、SeqreceiveAnd SeqlengthRepresent that transmission monitoring data sequent, reception monitoring data sequent and sequence are long respectively
Degree;The Hamming weight of sequence is sought in Hammingweight () expressions, and XOR represents xor operation.
Preferred in above technical scheme, the mapping relations pass through expression formula 19) obtain:
In formula:F () is multivariate nonlinear regression analysis model;CiIt is that the uniformity of i-th kind of parameter is measured;N is phonetic feature
The number of parameter;It is c1,...,cNThe objective MOS scorings predicted by f ().
Apply the technical scheme of the present invention, effect is:
1st, Mel frequency scales are approached using MFCC, so as to stretch the low-frequency information and compacting high-frequency information of voice, it can be used
In voice robust analysis and speech recognition, suppress the feature dependent on speaker, retain the philological quality of voice segments.
2nd, the present invention set up subjective MOS and it is objective estimate and channel quality between mapping relations, obtain to subjectivity
MOS points of forecast model so that point closer subjective quality.
3rd, the inventive method step is simplified, easy to use, and is capable of the quality of effectively objective evaluation voice, independent of master
See and evaluate.
In addition to objects, features and advantages described above, the present invention also has other objects, features and advantages.
Below with reference to accompanying drawings, the present invention is further detailed explanation.
Brief description of the drawings
The accompanying drawing for constituting the part of the application is used for providing a further understanding of the present invention, schematic reality of the invention
Apply example and its illustrate to be used to explain the present invention, do not constitute inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 is the principle schematic diagram of the appraisal procedure of the Objective speech quality based on output in embodiment 1.
Embodiment
Embodiments of the invention are described in detail below in conjunction with accompanying drawing, but the present invention can be limited according to claim
Fixed and covering multitude of different ways is implemented.
Embodiment 1:
A kind of appraisal procedure of the Objective speech quality based on output, refers to Fig. 1, specifically includes:Calculate and passed by system
Raw tone (is obtained distorted speech by the mel-frequency cepstrum coefficient of the distorted speech after defeated after system is transmitted;Calculate plum
Your process of frequency cepstral coefficient is MFCC parameter extraction process);The reference model that acquisition meets human hearing characteristic (is first carried
The MFCC parameters of reference voice are taken, then obtain GMM-HMM models);By the mel-frequency cepstrum coefficient of distorted speech with meeting people
The reference model of ear auditory properties carries out uniformity measure calculation (i.e. uniformity is calculated);One section of sequence is inserted in raw tone
Row, calculate the bit error rate that the sequence is extracted in the distorted speech after being transmitted by system;Measured and missed according to uniformity
Code check sets up the mapping relations between subjective MOS and homogeneity measure (i.e. MOS points of mappings in Fig. 1), obtains to be evaluated
Voice MOS points of objective forecast model, by the objective forecast model carry out voice quality objective evaluation (here by
The MOD of the mapping points of degrees of correlation and biased error between subjective MOS are used as evaluation criterion).Evaluation voice is ITU voices
Storehouse (International Telecommunication Union's sound bank), Details as Follows:
The calculating process of mel-frequency cepstrum coefficient includes pretreatment, FFT (Fast Fourier Transform (FFT)) conversion, Mel frequencies
Filtering and four steps of discrete cosine transform, be specifically:
The pretreatment specifically includes following steps:
Step 1.1, preemphasis, be specifically:Come using the digital filter of the lifting high frequency characteristics with 6dB/ octaves
Preemphasis is realized, its transmission function is expression formula 1):
H (z)=1- μ z-11);
Wherein:μ is pre emphasis factor, and its value is 0.9-1.0 (taking 0.95 herein);
Step 1.2, end-point detection, be specifically:Carried out by setting the thresholding of short-time energy and short-time zero-crossing rate, if certain
The Short Time Speech signal that individual length is N is x (m), its short-time energy E expression formulas 2) calculate:
Its short-time zero-crossing rate Z expression formulas 3) calculate:
Wherein, sgn [] is sign function, i.e.,:
Step 1.3, framing and adding window, be specifically:In order to be analyzed using the analysis method of stationary process, by language
Sound is divided into frame one by one, and the length of each frame is 10-30ms;Meanwhile, in order to reduce the truncation effect of speech frame, use
Hamming windows (hamming code window) carry out adding window to each frame signal, are specifically:
If frame signal is x (n), window function is w (n), then the signal y (n) after adding window is expression formula 4):
Y (n)=x (n) w (n), 0≤n≤N-1 4);
Wherein, N is the number of sampling per frame, and w (n) expression formula is w (n)=0.54-0.46cos [2 π n/ (N-1)], 0≤n≤
N-1。
The Mel frequency filterings are specifically:It will be filtered by the FFT discrete spectrums handled with sequence triangular filter
Processing, obtains one group of Coefficient ml、m2、……;The number p of the wave filter group is determined that all wave filters are total by the cut-off frequency of signal
Frequency (nyquist frequency), i.e. 1/2nd of sample rate are covered from 0Hz to Nyquist on body;miBy expression formula 5) calculate
Obtain:
Wherein:
F [i] is triangle filtering
The centre frequency of device, meets:Mel (f [i+1])-Mel (f [i])=Mel (f [i])-Mel (f [i-1]).
Because Mel spectral coefficients are all real numbers, time domain can be transformed to by discrete cosine transform.It is described discrete remaining
String is converted:, to time domain, Mel frequency cepstral coefficients will be obtained, it is by table by the Mel Spectrum Conversions of Mel frequency filterings
Up to formula 6) calculate obtain:
Wherein:MFCC (i) is Mel frequency cepstral coefficients, and N is points per frame sample, and P is the number of wave filter group.
The reference model detailed process that acquisition meets human hearing characteristic is as follows:
Pronunciation modeling and training based on GMM-HMM, if the characteristic vector sequence of observation is O=o1,o2,…,oT, the sequence
The state model sequence of row is S=s1,s2,…,sN, then the HMM model (hidden Markov model) of the sequence be expressed as expression formula
7):
λ=(π, A, B) is 7);
Wherein, π={ πi=P (s1=i), i=1,2 ..., N } it is initial state probabilities vector;A={ aijFor between state
The transition probability matrix redirected, aijTo jump to state j probability from state i;B={ bi(ot)=P (ot|st=i), 2≤i≤
N-1 } collect for the output probability distribution of state;
To continuous HMM model, observation sequence is continuous signal, and its signal space corresponding with state j is with M mixed Gaussian
Density function and represent, such as expression formula 8) and expression formula 9) under:
Wherein, cjkThe coefficient of expression state j k-th of Gaussian Mixture Model Probability Density Function;μjkIt is the average of Gaussian density function
Vector;CjkFor covariance matrix, D is observation sequence O dimension;HMM parameters are by observation sequence O=o1,o2,…,oTEstimate
Arrive, the target of estimation is that the likelihood function P (O | λ) for making model and training data maximizes to estimate newest λ, even ifThis can realize that the EM algorithms include two parts using EM algorithms (EM algorithm):Before
It is as follows to estimating again for backward probability calculation and HMM parameters and Gaussian mixture parameters:
The likelihood function p (O | λ) forward direction probability calculation formula such as expression formula 10):
Wherein:α1(i)=π bi(o1),1≤i≤N;
The likelihood function p (O | λ) backward probability calculation formula such as expression formula 11):
Wherein:βT(i)=1,1≤i≤N;
To giving observation sequence O=o1,o2,…,oTNewest λ is obtained by revaluation, ξ is defined hereintWhen (i, j) is t
Quarter state be siAnd t+1 moment state is sjProbability, by expression formula 12) obtain:
Under conditions of setting models λ and observation sequence O, state siIt is expression formula 13 in moment t posterior probability):
Thus, the revaluation of HMM parameter lambdas is as follows:
In the parameter c of t state k-th of Gaussian mixture components of jjk、μjkAnd CjkBy expression formula 14), 15) and 16) weight
New estimation:
Wherein, γt(j, k) represents the probability in t state k-th of Gaussian mixture components of j, can be obtained by following formula:
The computational methods that uniformity is measured are specifically:After modeling, the mel-frequency cepstrum coefficient of distorted speech and the ginseng
Model progress uniformity is examined to measure using expression formula 17) calculated:
Wherein:X1,...,XNIt is mel-frequency cepstrum coefficient (MFCC) vector of distorted speech, N is vectorial number, and C is to lose
The uniformity of true voice and model is measured.
The calculating process of the bit error rate is as follows:
Step A, one PN sequence of generation, and be multiplied with a chaos sequence, the generation of chaos sequence is reflected by logistic
Generation is penetrated, logistic mapping definitions are as follows:
xk+1=μ xk(1-xk)
Wherein, 0≤μ≤4 are referred to as branch parameter, xk∈ (0,1), when 3.5699456 ...<During μ≤4, logistic mappings
Work in the sequence { x that chaos state, i.e. primary condition are produced under logistic mappingsk;K=0,1,2,3 ... } it is aperiodic
, it is not convergent and very sensitive to initial value;Generate comprising the following steps that for monitoring data sequent:
Step a1, produce real-valued sequence first, and it is big for monitoring data sequent to choose the length that the position of some in sequence starts
Small one section;
Step a2, real-valued sequence is changed into binary sequence:By defining a threshold value Γ, obtained by real-valued sequence:
Binary chaotic sequence is { Γ (xk);K=0,1,2,3 ... };
Step a3, binary chaotic sequence is multiplied with a PN sequence (pseudo noise sequence), you can monitoring data sequent;
Step B, for monitoring data sequent insert synchronous code, monitoring data sequent embedded below is extracted frame by frame, be specifically:
Synchronous code is inserted for monitoring data sequent, the purpose of insertion synchronous code is that, in order to prevent audio after the decay of channel, receiving terminal is difficult
To extract monitoring data sequent;The synchronous code that we use is 16 bits, and in order to the code of positioning synchronous exactly, we adopt
The method taken is the embedded synchronous code in the time domain of voice signal, and concrete methods of realizing is by 16 sampled points before monitoring data sequent
Amplitude be set to 1000, so receiving terminal extract monitoring data sequent during, if there is the nonsynchronous situation of starting point, then may be used
With the sampled point using continuous 16 sample values 900~1100, rising for watermark is rapidly found out in the way of searching synchronous code
Beginning sample position, in this way, monitoring data sequent embedded below can be extracted frame by frame;
Step C, the monitoring data sequent for inserting synchronous code in embedded voice signal, selected embedding in wavelet field in wavelet field
The reason for entering is that embedded monitoring data sequent has more preferable disguised in transform domain, human ear will not be caused to distinguish to raw tone
Influence.The detailed process of sequence embedded voice in wavelet field is as follows:
Step c1, due to analyzing same problem using different wavelet basis different results can be produced, accordingly, it would be desirable to root
The problem of according to analysis, selects suitable wavelet basis, and Daubechies10 small echos are chosen herein and are used as wavelet function;
Step c2, sub-frame processing is carried out to voice signal, the size per frame is 1152 sampled points, and every frame signal is entered
3 layers of wavelet transformation of row;In view of the auditory properties of human ear, select to be embedded in sequence in high band herein;
Step c3, wavelet coefficient is quantified, and monitoring data sequent is modulated, so that monitoring data sequent is embedded in into voice
In signal, if coefficient to be quantified is f, the bit of embedded monitoring data sequent is w, and quantization step is Δ, and monitoring sequence is contained after quantization
The coefficient of column information concretely comprises the following steps for f':First to f modulus and floor operation, as f > 0, ifN=
M%2, then:
As f < 0, ifN=m%2, n=w, then:
Monitoring data sequent can be embedded into voice signal one by one according to above-mentioned formula.
Step c4, the signal of embedded monitoring data sequent switched back into time-domain signal;
Embedded monitoring data sequent is extracted in step D, the voice received, and calculates the bit error rate, details are:Monitoring data sequent
Extraction be embedded inverse process, therefore the wavelet function and the series of wavelet decomposition used all keep constant, specifically extract
Process comprises the following steps:
Step d1, synchronous code is searched in voice signal, be specifically:If needing the length that the signal length searched for is L, then L
Degree should be more than the length of two synchronous codes and the summation of a complete monitoring data sequent length.If the initiating searches point of signal is
I=1, if the sample value of signalIn the range of 900-1100, then it is assumed that searched possible synchronous code,
It is compared using default synchronous code;If determined as synchronous code, then I points are the original position of monitoring data sequent, otherwise make I
=I+L;
Step d2, since the starting point found, to voice signal carry out wavelet transform;
Step d3, the operation for making contrary during with insertion to the coefficient f after wavelet decomposition, i.e.,:
During f > 0, ifW=m%2;
During f < 0, ifW=m%2;
So as to extract binary system monitoring data sequent;
Step d4, compare the monitoring data sequent extracted and the monitoring data sequent of insertion, by expression formula 18) calculate the bit error rate
(bit error rate as one of speech quality evaluation objective estimate):
Wherein Seqsend、SeqreceiveAnd SeqlengthRepresent that transmission monitoring data sequent, reception monitoring data sequent and sequence are long respectively
Degree;The Hamming weight of sequence is sought in Hammingweight () expressions, and XOR represents xor operation.
After the parameter consistency of voice under calculating various distortion conditions is measured, a kind of Function Mapping relation can be used
Come represent parameter consistency measure with it is objectiveBetween relation, i.e., described mapping relations pass through expression formula 19) obtain:
In formula:F () is that (it can be linearly or nonlinearly regression relation or fitting of a polynomial to anticipation function
Relation, in this patent embodiment, in order to obtain more accurately predicting MOS values, preferred multivariate nonlinear regression analysis model herein);
CiIt is that the uniformity of i-th kind of parameter is measured;N is the number of speech characteristic parameter;It is c1,...,cNPredicted by f ()
The objective MOS scorings gone out.The bit error rate is bigger, illustrates to disturb stronger in channel, the speech damage brought in transmitting procedure is also corresponding
Also it is big, it is correspondingValue is smaller, and the quality of voice is poorer.
The performance of speech quality evaluation algorithm is weighed from the degree of correlation, biased error below.The degree of correlation mainly reflects voice
Whether the mapping relations that quality evaluation algorithm obtains MOS points of prediction by distortion map are reasonable, the general MOS with Algorithm mapping points
Degree of correlation and biased error between known subjective MOS values are used as evaluation criterion.
Correlation coefficient ρ and pass through expression formula 20 with standard estimated bias σ) and expression formula 21) obtain:
Wherein:MOSo(i) be i-th of voice prediction MOS values, MOSs(i) it is known MOS points, N is total voice pair
Number,The average of prediction MOS values is represented,Represent the average that MOS divides.
Correlation coefficient ρ is closer to 1, and prediction MOS values are closer to true MOS values;Biased error σ is smaller, then predicated error is got over
Small, the performance of algorithm is better.
The appraisal procedure of the present embodiment 1 and International Telecommunication Union ITU P.563 method for objectively evaluating (ITU-TP.563)
Performance comparison is the results detailed in Table 1.
From table 1 it follows that the inventive method (embodiment 1) is certain relative to having on ITU-TP.563 algorithm performances
The raising of degree, the average degree of correlation ρ of subjective MOS is higher, and estimated bias σ is relatively low, therefore, and the inventive method has validity
And feasibility.
The performance comparision table that the inventive method of table 1 (embodiment 1) and ITU-TP.563 are handled voice respectively
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.Within the spirit and principles of the invention, that is made any repaiies
Change, equivalent substitution, improvement etc., should be included in the scope of the protection.
Claims (10)
1. a kind of appraisal procedure of the Objective speech quality based on output, it is characterised in that comprise the following steps:
Calculate the mel-frequency cepstrum coefficient of the distorted speech after system is transmitted;Obtain the reference for meeting human hearing characteristic
Model;
The mel-frequency cepstrum coefficient of distorted speech and the reference model progress uniformity for meeting human hearing characteristic are measured into meter
Calculate;One section of sequence is inserted in raw tone, calculating extracts the sequence in the distorted speech after being transmitted by system
The bit error rate;
Measured and mapping relations that the bit error rate is set up between subjective MOS and homogeneity measure, obtained to be evaluated according to uniformity
The objective forecast model that MOS points of valency voice, the objective evaluation of voice quality is carried out by the objective forecast model.
2. the appraisal procedure of the Objective speech quality according to claim 1 based on output, it is characterised in that:The Mel
The calculating process of frequency cepstral coefficient includes pretreatment, FFT, four steps of Mel frequency filterings and discrete cosine transform.
3. the appraisal procedure of the Objective speech quality according to claim 2 based on output, it is characterised in that:
The pretreatment specifically includes following steps:
Step 1.1, preemphasis, be specifically:Realized using the digital filter of the lifting high frequency characteristics with 6dB/ octaves
Preemphasis, its transmission function is expression formula 1):
H (z)=1- μ z-11);
Wherein:μ is pre emphasis factor, and its value is 0.9-1.0;
Step 1.2, end-point detection, be specifically:Carried out by setting the thresholding of short-time energy and short-time zero-crossing rate, if some is grown
The Short Time Speech signal that degree is N is x (m), its short-time energy E expression formulas 2) calculate:
<mrow>
<mi>E</mi>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>m</mi>
<mo>=</mo>
<mn>0</mn>
</mrow>
<mrow>
<mi>N</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</munderover>
<msup>
<mi>x</mi>
<mn>2</mn>
</msup>
<mrow>
<mo>(</mo>
<mi>m</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mn>2</mn>
<mo>)</mo>
<mo>;</mo>
</mrow>
Its short-time zero-crossing rate Z expression formulas 3) calculate:
<mrow>
<mi>Z</mi>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mn>2</mn>
</mfrac>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>m</mi>
<mo>=</mo>
<mn>0</mn>
</mrow>
<mrow>
<mi>N</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</munderover>
<mo>|</mo>
<mi>sgn</mi>
<mo>&lsqb;</mo>
<mi>x</mi>
<mrow>
<mo>(</mo>
<mi>m</mi>
<mo>)</mo>
</mrow>
<mo>&rsqb;</mo>
<mo>-</mo>
<mi>sgn</mi>
<mo>&lsqb;</mo>
<mi>x</mi>
<mrow>
<mo>(</mo>
<mi>m</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>&rsqb;</mo>
<mo>|</mo>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mn>3</mn>
<mo>)</mo>
<mo>;</mo>
</mrow>
Wherein, sgn [] is sign function, i.e.,:
Step 1.3, framing and adding window, be specifically:The framing is that voice is divided into frame one by one, and the length of each frame is
10-30ms;The adding window is to carry out adding window to each frame signal using Hamming windows.
4. the appraisal procedure of the Objective speech quality according to claim 3 based on output, it is characterised in that:The adding window
Detailed process be:If frame signal is x (n), window function is w (n), then the signal y (n) after adding window is expression formula 4):
Y (n)=x (n) w (n), 0≤n≤N-1 4);
Wherein, N is the number of sampling per frame, and w (n) expression formula is w (n)=0.54-0.46cos [2 π n/ (N-1)], 0≤n≤
N-1。
5. the appraisal procedure of the Objective speech quality according to claim 2 based on output, it is characterised in that:The Mel
Frequency filtering is specifically:The discrete spectrum handled by FFT is filtered processing with sequence triangular filter, a system is obtained
Number ml、m2、……;The number p of the wave filter group determines by the cut-off frequency of signal, all wave filters generally cover from 0Hz to
/ 2nd of Nyquist frequencies, i.e. sample rate;miBy expression formula 5) calculate obtain:
<mrow>
<msub>
<mi>m</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<mi>l</mi>
<mi>n</mi>
<mrow>
<mo>(</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>0</mn>
</mrow>
<mrow>
<mi>N</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</munderover>
<mo>|</mo>
<mi>X</mi>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
<mo>|</mo>
<mo>&CenterDot;</mo>
<msub>
<mi>H</mi>
<mi>i</mi>
</msub>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mo>,</mo>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
<mo>,</mo>
<mn>2</mn>
<mo>,</mo>
<mo>...</mo>
<mo>,</mo>
<mi>p</mi>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mn>5</mn>
<mo>)</mo>
<mo>;</mo>
</mrow>
Wherein:
F [i] is the centre frequency of triangular filter, is met:Mel (f [i+1])-Mel (f [i])=Mel (f [i])-Mel (f [i-
1]);X (k) is the discrete spectrum after frame signal x (n) is handled through FFT.
6. the appraisal procedure of the Objective speech quality according to claim 2 based on output, it is characterised in that:It is described discrete
Cosine transform is specifically:Will by Mel frequency filterings Mel Spectrum Conversions to time domain, obtain Mel frequency cepstral coefficients, its by
Expression formula 6) calculate obtain:
<mrow>
<mi>M</mi>
<mi>F</mi>
<mi>C</mi>
<mi>C</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msqrt>
<mrow>
<mfrac>
<mn>2</mn>
<mi>N</mi>
</mfrac>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>P</mi>
</munderover>
<msub>
<mi>m</mi>
<mi>j</mi>
</msub>
<mi>c</mi>
<mi>o</mi>
<mi>s</mi>
<mo>&lsqb;</mo>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>-</mo>
<mn>0.5</mn>
<mo>)</mo>
</mrow>
<mfrac>
<mrow>
<mi>&pi;</mi>
<mi>i</mi>
</mrow>
<mi>p</mi>
</mfrac>
<mo>&rsqb;</mo>
</mrow>
</msqrt>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mn>6</mn>
<mo>)</mo>
<mo>;</mo>
</mrow>
Wherein:MFCC (i) is Mel frequency cepstral coefficients, and N is points per frame sample, and P is the number of wave filter group.
7. the appraisal procedure of the Objective speech quality according to claim 1 based on output, it is characterised in that:Met
The reference model detailed process of human hearing characteristic is as follows:
If the characteristic vector sequence of observation is O=o1,o2,…,oT, the state model sequence of the sequence is S=s1,s2,…,sN,
Then the HMM model of the sequence is expressed as expression formula 7):
λ=(π, A, B) is 7);
Wherein, π={ πi=P (s1=i), i=1,2 ..., N } it is initial state probabilities vector;A={ aijFor what is redirected between state
Transition probability matrix, aijTo jump to state j probability from state i;B={ bi(ot)=P (ot|st=i), 2≤i≤N-1 } be
The output probability distribution collection of state;
To continuous HMM model, observation sequence is continuous signal, and its signal space corresponding with state j is with M mixed Gaussian density
Function and represent, such as expression formula 8) and expression formula 9) under:
<mrow>
<msub>
<mi>b</mi>
<mi>j</mi>
</msub>
<mrow>
<mo>(</mo>
<msub>
<mi>o</mi>
<mi>t</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>M</mi>
</munderover>
<msub>
<mi>c</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
</msub>
<mi>N</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>o</mi>
<mi>t</mi>
</msub>
<mo>,</mo>
<msub>
<mi>&mu;</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
</msub>
<mo>,</mo>
<msub>
<mi>C</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mo>,</mo>
<mn>1</mn>
<mo>&le;</mo>
<mi>j</mi>
<mo>&le;</mo>
<mi>N</mi>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mn>8</mn>
<mo>)</mo>
<mo>;</mo>
</mrow>
<mrow>
<mi>N</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>o</mi>
<mi>t</mi>
</msub>
<mo>,</mo>
<msub>
<mi>&mu;</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
</msub>
<mo>,</mo>
<msub>
<mi>C</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msup>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mi>&pi;</mi>
<mo>)</mo>
</mrow>
<mrow>
<mo>-</mo>
<mi>D</mi>
<mo>/</mo>
<mn>2</mn>
</mrow>
</msup>
<mo>|</mo>
<msub>
<mi>C</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
</msub>
<msup>
<mo>|</mo>
<mrow>
<mo>-</mo>
<mn>1</mn>
<mo>/</mo>
<mn>2</mn>
</mrow>
</msup>
<mi>exp</mi>
<mrow>
<mo>(</mo>
<mo>-</mo>
<mfrac>
<mn>1</mn>
<mn>2</mn>
</mfrac>
<msup>
<mrow>
<mo>(</mo>
<mrow>
<msub>
<mi>o</mi>
<mi>t</mi>
</msub>
<mo>-</mo>
<msub>
<mi>&mu;</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
</msub>
</mrow>
<mo>)</mo>
</mrow>
<mi>T</mi>
</msup>
<msubsup>
<mi>C</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
<mrow>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
<mo>(</mo>
<mrow>
<msub>
<mi>o</mi>
<mi>t</mi>
</msub>
<mo>-</mo>
<msub>
<mi>&mu;</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
</msub>
</mrow>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mn>9</mn>
<mo>)</mo>
<mo>;</mo>
</mrow>
Wherein, cjkThe coefficient of expression state j k-th of Gaussian Mixture Model Probability Density Function;μjkIt is the mean vector of Gaussian density function;
CjkFor covariance matrix, D is observation sequence O dimension;HMM parameters are by observation sequence O=o1,o2,…,oTEstimation is obtained, estimation
Target be that the likelihood function P (O | λ) for making model and training data maximizes to estimate newest λ, even if
The likelihood function p (O | λ) forward direction probability calculation formula such as expression formula 10):
<mrow>
<mi>P</mi>
<mrow>
<mo>(</mo>
<mi>O</mi>
<mo>|</mo>
<mi>&lambda;</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>&alpha;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mn>10</mn>
<mo>)</mo>
<mo>;</mo>
</mrow>
Wherein:α1(i)=π bi(o1),1≤i≤N;
<mrow>
<msub>
<mi>&alpha;</mi>
<mrow>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mo>&lsqb;</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>&alpha;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<msub>
<mi>a</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<mo>&rsqb;</mo>
<msub>
<mi>b</mi>
<mi>j</mi>
</msub>
<mrow>
<mo>(</mo>
<msub>
<mi>o</mi>
<mrow>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mo>,</mo>
<mn>1</mn>
<mo>&le;</mo>
<mi>t</mi>
<mo>&le;</mo>
<mi>T</mi>
<mo>-</mo>
<mn>1</mn>
<mo>,</mo>
<mn>1</mn>
<mo>&le;</mo>
<mi>j</mi>
<mo>&le;</mo>
<mi>N</mi>
<mo>;</mo>
</mrow>
The likelihood function p (O | λ) backward probability calculation formula such as expression formula 11):
<mrow>
<mi>P</mi>
<mrow>
<mo>(</mo>
<mi>O</mi>
<mo>|</mo>
<mi>&lambda;</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>&pi;</mi>
<mi>i</mi>
</msub>
<msub>
<mi>b</mi>
<mn>1</mn>
</msub>
<mrow>
<mo>(</mo>
<msub>
<mi>o</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<msub>
<mi>&beta;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mn>11</mn>
<mo>)</mo>
<mo>;</mo>
</mrow>
Wherein:βT(i)=1,1≤i≤N;
<mrow>
<msub>
<mi>&beta;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>a</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<msub>
<mi>b</mi>
<mi>j</mi>
</msub>
<mrow>
<mo>(</mo>
<msub>
<mi>o</mi>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<msub>
<mi>&beta;</mi>
<mrow>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
<mo>,</mo>
<mn>1</mn>
<mo>&le;</mo>
<mi>j</mi>
<mo>&le;</mo>
<mi>N</mi>
<mo>,</mo>
<mi>t</mi>
<mo>=</mo>
<mi>T</mi>
<mo>-</mo>
<mn>1</mn>
<mo>,</mo>
<mi>T</mi>
<mo>-</mo>
<mn>2</mn>
<mo>,</mo>
<mo>...</mo>
<mo>,</mo>
<mn>1</mn>
<mo>;</mo>
</mrow>
To giving observation sequence O=o1,o2,…,oTNewest λ is obtained by revaluation, ξ is defined hereint(i, j) is t shape
State is siAnd t+1 moment state is sjProbability, by expression formula 12) obtain:
<mrow>
<mtable>
<mtr>
<mtd>
<mrow>
<msub>
<mi>&xi;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msub>
<mi>P</mi>
<mrow>
<mi>S</mi>
<mo>|</mo>
<mi>O</mi>
<mo>,</mo>
<mi>&lambda;</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<msub>
<mi>s</mi>
<mi>t</mi>
</msub>
<mo>=</mo>
<msub>
<mi>s</mi>
<mi>i</mi>
</msub>
<mo>,</mo>
<msub>
<mi>s</mi>
<mrow>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>=</mo>
<msub>
<mi>s</mi>
<mi>j</mi>
</msub>
<mo>|</mo>
<mi>O</mi>
<mo>,</mo>
<mi>&lambda;</mi>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>=</mo>
<mfrac>
<mrow>
<msub>
<mi>&alpha;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<msub>
<mi>a</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<msub>
<mi>b</mi>
<mi>j</mi>
</msub>
<mrow>
<mo>(</mo>
<msub>
<mi>o</mi>
<mrow>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<msub>
<mi>&beta;</mi>
<mrow>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>&alpha;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<msub>
<mi>a</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<msub>
<mi>b</mi>
<mi>j</mi>
</msub>
<mrow>
<mo>(</mo>
<msub>
<mi>o</mi>
<mrow>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<msub>
<mi>&beta;</mi>
<mrow>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
</mrow>
</mtd>
</mtr>
</mtable>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mn>12</mn>
<mo>)</mo>
<mo>;</mo>
</mrow>
Under conditions of setting models λ and observation sequence O, state siIt is expression formula 13 in moment t posterior probability):
<mrow>
<mtable>
<mtr>
<mtd>
<mrow>
<msub>
<mi>&gamma;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msub>
<mi>P</mi>
<mrow>
<mi>S</mi>
<mo>|</mo>
<mi>O</mi>
<mo>,</mo>
<mi>&lambda;</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mrow>
<msub>
<mi>s</mi>
<mi>t</mi>
</msub>
<mo>=</mo>
<mi>i</mi>
<mo>|</mo>
<mi>O</mi>
<mo>,</mo>
<mi>&lambda;</mi>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>=</mo>
<mfrac>
<mrow>
<msub>
<mi>&alpha;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<msub>
<mi>&beta;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>&alpha;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<msub>
<mi>&beta;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>=</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>&xi;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
</mtable>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mn>13</mn>
<mo>)</mo>
<mo>;</mo>
</mrow>
Thus, the revaluation of HMM parameter lambdas is as follows:
<mrow>
<msub>
<mover>
<mi>&pi;</mi>
<mo>&OverBar;</mo>
</mover>
<mi>i</mi>
</msub>
<mo>=</mo>
<msub>
<mi>&gamma;</mi>
<mn>1</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>;</mo>
</mrow>
<mrow>
<msub>
<mover>
<mi>a</mi>
<mo>&OverBar;</mo>
</mover>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>t</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mrow>
<mi>T</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</munderover>
<msub>
<mi>&xi;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>t</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mrow>
<mi>T</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</munderover>
<msub>
<mi>&gamma;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>;</mo>
</mrow>
In the parameter c of t state k-th of Gaussian mixture components of jjk, μjkAnd CjkBy expression formula 14), 15) and 16) estimate again
Meter:
<mrow>
<msub>
<mover>
<mi>c</mi>
<mo>&OverBar;</mo>
</mover>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>t</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>T</mi>
</munderover>
<msub>
<mi>&gamma;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>,</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>t</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>T</mi>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>M</mi>
</munderover>
<msub>
<mi>&gamma;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>,</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mn>14</mn>
<mo>)</mo>
<mo>;</mo>
</mrow>
<mrow>
<msub>
<mover>
<mi>&mu;</mi>
<mo>&OverBar;</mo>
</mover>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>t</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>T</mi>
</munderover>
<msub>
<mi>&gamma;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>,</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<msub>
<mi>o</mi>
<mi>t</mi>
</msub>
</mrow>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>t</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>T</mi>
</munderover>
<msub>
<mi>&gamma;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>,</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mn>15</mn>
<mo>)</mo>
<mo>;</mo>
</mrow>
<mrow>
<msub>
<mover>
<mi>C</mi>
<mo>&OverBar;</mo>
</mover>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>t</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>T</mi>
</munderover>
<msub>
<mi>&gamma;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mrow>
<mi>j</mi>
<mo>,</mo>
<mi>k</mi>
</mrow>
<mo>)</mo>
</mrow>
<mrow>
<mo>(</mo>
<mrow>
<msub>
<mi>o</mi>
<mi>t</mi>
</msub>
<mo>-</mo>
<msub>
<mi>&mu;</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
</msub>
</mrow>
<mo>)</mo>
</mrow>
<msup>
<mrow>
<mo>(</mo>
<mrow>
<msub>
<mi>o</mi>
<mi>t</mi>
</msub>
<mo>-</mo>
<msub>
<mi>&mu;</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
</msub>
</mrow>
<mo>)</mo>
</mrow>
<mi>T</mi>
</msup>
</mrow>
<mrow>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>t</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>T</mi>
</munderover>
<msub>
<mi>&gamma;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mrow>
<mi>j</mi>
<mo>,</mo>
<mi>k</mi>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mn>16</mn>
<mo>)</mo>
<mo>;</mo>
</mrow>
Wherein, γt(j, k) represents the probability in t state k-th of Gaussian mixture components of j, can be obtained by following formula:
<mrow>
<msub>
<mi>&gamma;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>,</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mrow>
<msub>
<mi>&alpha;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
<msub>
<mi>&beta;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>&alpha;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<msub>
<mi>&beta;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>&lsqb;</mo>
<mfrac>
<mrow>
<msub>
<mi>c</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
</msub>
<mi>N</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>o</mi>
<mi>t</mi>
</msub>
<mo>,</mo>
<msub>
<mi>&mu;</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
</msub>
<mo>,</mo>
<msub>
<mi>C</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>m</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>M</mi>
</munderover>
<msub>
<mi>c</mi>
<mrow>
<mi>j</mi>
<mi>m</mi>
</mrow>
</msub>
<mi>N</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>o</mi>
<mi>t</mi>
</msub>
<mo>,</mo>
<msub>
<mi>&mu;</mi>
<mrow>
<mi>j</mi>
<mi>m</mi>
</mrow>
</msub>
<mo>,</mo>
<msub>
<mi>C</mi>
<mrow>
<mi>j</mi>
<mi>m</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>&rsqb;</mo>
<mo>.</mo>
</mrow>
8. the appraisal procedure of the Objective speech quality according to claim 1 based on output, it is characterised in that:Uniformity amount
The computational methods of degree are specifically:Using expression formula 17) calculated:
<mrow>
<mi>C</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>X</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<mo>...</mo>
<mo>,</mo>
<msub>
<mi>X</mi>
<mi>N</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mi>N</mi>
</mfrac>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<mi>l</mi>
<mi>o</mi>
<mi>g</mi>
<mrow>
<mo>(</mo>
<mi>P</mi>
<mo>(</mo>
<mrow>
<msub>
<mi>X</mi>
<mi>j</mi>
</msub>
<mo>|</mo>
<mi>&lambda;</mi>
</mrow>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mn>17</mn>
<mo>)</mo>
<mo>;</mo>
</mrow>
Wherein:X1,...,XNIt is the mel-frequency cepstrum coefficient vector of distorted speech, N is vectorial number, and C is distorted speech and mould
The uniformity of type is measured.
9. the appraisal procedure of the Objective speech quality according to claim 1 based on output, it is characterised in that:The error code
The calculating process of rate is as follows:
Step A, one PN sequence of generation, and be multiplied with a chaos sequence, the generation of chaos sequence is mapped by logistic produces
Raw, logistic mapping definitions are as follows:
xk+1=μ xk(1-xk)
Wherein, 0≤μ≤4 are referred to as branch parameter, xk∈ (0,1), when 3.5699456 ...<During μ≤4, logistic mappings works in
Sequence { the x that chaos state, i.e. primary condition are produced under logistic mappingsk;K=0,1,2,3 ... } it is aperiodic, does not receive
It is holding back and very sensitive to initial value;Generate comprising the following steps that for monitoring data sequent:
Step a1, produce real-valued sequence first, and it is monitoring data sequent size to choose the length that the position of some in sequence starts
One section;
Step a2, real-valued sequence is changed into binary sequence:By defining a threshold value Γ, obtained by real-valued sequence:
<mrow>
<mi>&Gamma;</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mo>-</mo>
<mn>1</mn>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>x</mi>
<mo><</mo>
<mi>&Gamma;</mi>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>1</mn>
</mtd>
<mtd>
<mrow>
<mi>&Gamma;</mi>
<mo>&le;</mo>
<mi>x</mi>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>;</mo>
</mrow>
Binary chaotic sequence is { Γ (xk);K=0,1,2,3 ... };
Step a3, binary chaotic sequence is multiplied with a PN sequence, you can obtain monitoring data sequent;
Step B, for monitoring data sequent insert synchronous code, monitoring data sequent embedded below is extracted frame by frame;
Step C, the monitoring data sequent of synchronous code will be inserted in wavelet field in embedded voice signal, detailed process is as follows:
Step c1, selection Daubechies10 small echos are used as wavelet function;
Step c2, sub-frame processing is carried out to voice signal, the size per frame is 1152 sampled points, and carries out 3 to every frame signal
Layer wavelet transformation;
Step c3, wavelet coefficient is quantified, and monitoring data sequent is modulated, so that monitoring data sequent is embedded in into voice signal
In, if coefficient to be quantified is f, the bit of embedded monitoring data sequent is w, and quantization step is Δ, is believed after quantization containing monitoring data sequent
The coefficient of breath concretely comprises the following steps for f':
To f modulus and floor operation, as f > 0, ifN=m%2, then:
As f < 0, ifN=m%2, n=w, then:
Monitoring data sequent is embedded into voice signal one by one according to above-mentioned formula;
Step c4, the signal of embedded monitoring data sequent switched back into time-domain signal;
Embedded monitoring data sequent is extracted in step D, the voice received, and calculates the bit error rate, the process specifically extracted includes
Following steps:
Step d1, synchronous code is searched in voice signal, be specifically:If it is L to need the signal length searched for, then L length should
When the length more than two synchronous codes and the summation of a complete monitoring data sequent length;If the initiating searches point of signal is I=
1, if the sample value of signalIn the range of 900-1100, then it is assumed that searched possible synchronous code, profit
It is compared with default synchronous code;If determined as synchronous code, then I points are the original position of monitoring data sequent, otherwise make I=
I+L;
Step d2, since the starting point found, to voice signal carry out wavelet transform;
Step d3, the operation for making contrary during with insertion to the coefficient f after wavelet decomposition, i.e.,:During f > 0, ifw
=m%2;During f < 0, ifW=m%2;
So as to extract binary system monitoring data sequent;
Step d4, compare the monitoring data sequent extracted and the monitoring data sequent of insertion, by expression formula 18) calculate the bit error rate:
<mrow>
<mi>B</mi>
<mi>E</mi>
<mi>R</mi>
<mo>=</mo>
<mfrac>
<mrow>
<mi>H</mi>
<mi>a</mi>
<mi>m</mi>
<mi>min</mi>
<mi>g</mi>
<mi>W</mi>
<mi>e</mi>
<mi>i</mi>
<mi>g</mi>
<mi>h</mi>
<mi>t</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>Seq</mi>
<mrow>
<mi>s</mi>
<mi>e</mi>
<mi>n</mi>
<mi>d</mi>
</mrow>
</msub>
<mi>X</mi>
<mi>O</mi>
<mi>R</mi>
<mi> </mi>
<msub>
<mi>Seq</mi>
<mrow>
<mi>r</mi>
<mi>e</mi>
<mi>c</mi>
<mi>e</mi>
<mi>i</mi>
<mi>v</mi>
<mi>e</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msub>
<mi>Seq</mi>
<mrow>
<mi>l</mi>
<mi>e</mi>
<mi>n</mi>
<mi>g</mi>
<mi>t</mi>
<mi>h</mi>
</mrow>
</msub>
</mrow>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mn>18</mn>
<mo>)</mo>
<mo>;</mo>
</mrow>
Wherein Seqsend、SeqreceiveAnd SeqlengthRepresent to send monitoring data sequent respectively, receive monitoring data sequent and sequence length;
The Hamming weight of sequence is sought in Hammingweight () expressions, and XOR represents xor operation.
10. the appraisal procedure of the Objective speech quality according to claim 1 based on output, it is characterised in that:It is described to reflect
Penetrate relation and pass through expression formula 19) obtain:
In formula:F () is multivariate nonlinear regression analysis model;CiIt is that the uniformity of i-th kind of parameter is measured;N is speech characteristic parameter
Number;It is c1,...,cNThe objective MOS scorings predicted by f ().
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710475912.8A CN107293306B (en) | 2017-06-21 | 2017-06-21 | A kind of appraisal procedure of the Objective speech quality based on output |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710475912.8A CN107293306B (en) | 2017-06-21 | 2017-06-21 | A kind of appraisal procedure of the Objective speech quality based on output |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107293306A true CN107293306A (en) | 2017-10-24 |
CN107293306B CN107293306B (en) | 2018-06-15 |
Family
ID=60096759
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710475912.8A Active CN107293306B (en) | 2017-06-21 | 2017-06-21 | A kind of appraisal procedure of the Objective speech quality based on output |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107293306B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107818797A (en) * | 2017-12-07 | 2018-03-20 | 苏州科达科技股份有限公司 | Voice quality assessment method, apparatus and its system |
CN108364661A (en) * | 2017-12-15 | 2018-08-03 | 海尔优家智能科技(北京)有限公司 | Visualize speech performance appraisal procedure, device, computer equipment and storage medium |
CN110211566A (en) * | 2019-06-08 | 2019-09-06 | 安徽中医药大学 | A kind of classification method of compressed sensing based hepatolenticular degeneration disfluency |
CN110289014A (en) * | 2019-05-21 | 2019-09-27 | 华为技术有限公司 | A kind of speech quality detection method and electronic equipment |
CN111091816A (en) * | 2020-03-19 | 2020-05-01 | 北京五岳鑫信息技术股份有限公司 | Data processing system and method based on voice evaluation |
CN111968677A (en) * | 2020-08-21 | 2020-11-20 | 南京工程学院 | Voice quality self-evaluation method for fitting-free hearing aid |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040186716A1 (en) * | 2003-01-21 | 2004-09-23 | Telefonaktiebolaget Lm Ericsson | Mapping objective voice quality metrics to a MOS domain for field measurements |
CN1713273A (en) * | 2005-07-21 | 2005-12-28 | 复旦大学 | Algorithm of local robust digital voice-frequency watermark for preventing time size pantography |
CN101847409A (en) * | 2010-03-25 | 2010-09-29 | 北京邮电大学 | Voice integrity protection method based on digital fingerprint |
CN102044248A (en) * | 2009-10-10 | 2011-05-04 | 北京理工大学 | Objective evaluating method for audio quality of streaming media |
CN102881289A (en) * | 2012-09-11 | 2013-01-16 | 重庆大学 | Hearing perception characteristic-based objective voice quality evaluation method |
-
2017
- 2017-06-21 CN CN201710475912.8A patent/CN107293306B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040186716A1 (en) * | 2003-01-21 | 2004-09-23 | Telefonaktiebolaget Lm Ericsson | Mapping objective voice quality metrics to a MOS domain for field measurements |
CN1713273A (en) * | 2005-07-21 | 2005-12-28 | 复旦大学 | Algorithm of local robust digital voice-frequency watermark for preventing time size pantography |
CN102044248A (en) * | 2009-10-10 | 2011-05-04 | 北京理工大学 | Objective evaluating method for audio quality of streaming media |
CN101847409A (en) * | 2010-03-25 | 2010-09-29 | 北京邮电大学 | Voice integrity protection method based on digital fingerprint |
CN102881289A (en) * | 2012-09-11 | 2013-01-16 | 重庆大学 | Hearing perception characteristic-based objective voice quality evaluation method |
Non-Patent Citations (4)
Title |
---|
QINGXIAN LI ETC: "A Speech Quality Evaluation Method Based on Auditory Characteristic", 《PROCEEDINGS OF THE 2016 INTERNATIONAL CONFERENCE ON INTELLIGENT CONTROL AND COMPUTER APPLICATION(ICCA 2016)》 * |
宋知用: "《Matlab在语音信号分析与合成中的应用》", 30 November 2013, 北京航空航天大学出版社 * |
陆虎敏: "《飞机座舱显示与控制技术》", 31 December 2015, 航空工业出版社 * |
韩志艳 等: "《语音信号鲁棒特征提取及可视化技术研究》", 29 February 2012, 东北大学出版社 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107818797A (en) * | 2017-12-07 | 2018-03-20 | 苏州科达科技股份有限公司 | Voice quality assessment method, apparatus and its system |
CN108364661A (en) * | 2017-12-15 | 2018-08-03 | 海尔优家智能科技(北京)有限公司 | Visualize speech performance appraisal procedure, device, computer equipment and storage medium |
CN110289014A (en) * | 2019-05-21 | 2019-09-27 | 华为技术有限公司 | A kind of speech quality detection method and electronic equipment |
CN110289014B (en) * | 2019-05-21 | 2021-11-19 | 华为技术有限公司 | Voice quality detection method and electronic equipment |
CN110211566A (en) * | 2019-06-08 | 2019-09-06 | 安徽中医药大学 | A kind of classification method of compressed sensing based hepatolenticular degeneration disfluency |
CN111091816A (en) * | 2020-03-19 | 2020-05-01 | 北京五岳鑫信息技术股份有限公司 | Data processing system and method based on voice evaluation |
CN111968677A (en) * | 2020-08-21 | 2020-11-20 | 南京工程学院 | Voice quality self-evaluation method for fitting-free hearing aid |
CN111968677B (en) * | 2020-08-21 | 2021-09-07 | 南京工程学院 | Voice quality self-evaluation method for fitting-free hearing aid |
Also Published As
Publication number | Publication date |
---|---|
CN107293306B (en) | 2018-06-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107293306B (en) | A kind of appraisal procedure of the Objective speech quality based on output | |
CN108447495B (en) | Deep learning voice enhancement method based on comprehensive feature set | |
CN1121681C (en) | Speech processing | |
CN1750124B (en) | Bandwidth extension of band limited audio signals | |
WO2019232829A1 (en) | Voiceprint recognition method and apparatus, computer device and storage medium | |
US7720012B1 (en) | Speaker identification in the presence of packet losses | |
EP3910630B1 (en) | Transient speech or audio signal encoding method and device, decoding method and device, processing system and computer-readable storage medium | |
CN110428842A (en) | Speech model training method, device, equipment and computer readable storage medium | |
CN111696580B (en) | Voice detection method and device, electronic equipment and storage medium | |
Dubey et al. | Non-intrusive speech quality assessment using several combinations of auditory features | |
CN104361894A (en) | Output-based objective voice quality evaluation method | |
CN109036470A (en) | Speech differentiation method, apparatus, computer equipment and storage medium | |
CN101577116A (en) | Extracting method of MFCC coefficients of voice signal, device and Mel filtering method | |
CN108806725A (en) | Speech differentiation method, apparatus, computer equipment and storage medium | |
CN105741853A (en) | Digital speech perception hash method based on formant frequency | |
Lim et al. | Classification of underwater transient signals using mfcc feature vector | |
CN103971697B (en) | Sound enhancement method based on non-local mean filtering | |
CN116153337B (en) | Synthetic voice tracing evidence obtaining method and device, electronic equipment and storage medium | |
Gandhiraj et al. | Auditory-based wavelet packet filterbank for speech recognition using neural network | |
Varela et al. | Combining pulse-based features for rejecting far-field speech in a HMM-based voice activity detector | |
CN105206259A (en) | Voice conversion method | |
CN112233693B (en) | Sound quality evaluation method, device and equipment | |
Mahdi et al. | New single-ended objective measure for non-intrusive speech quality evaluation | |
CN113012684B (en) | Synthesized voice detection method based on voice segmentation | |
CN114023343A (en) | Voice conversion method based on semi-supervised feature learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |