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
  • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
  • G10L25/69—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for evaluating synthetic or decoded voice signals
• • 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

Definitions

• the invention relates to a method for instrumental ("objective") speech quality determination, in which characteristic values for determining the speech quality (speech quality) are derived by comparing properties of a speech signal to be evaluated with properties of a reference speech signal (undisturbed signal).
• Speech quality determinations of speech signals are generally carried out by means of auditory ("subjective") examinations with test subjects.
• the aim of instrumental ("objective") methods for determining speech quality is to determine from the properties of the speech signal to be assessed, using suitable computing methods, characteristic values which describe the speech quality of the speech signal to be assessed, without having to resort to judgments from test subjects.
• the calculated parameters and the underlying method for instrumental language quality determination are considered recognized if a high correlation to the results of auditory comparative examinations is achieved.
• the language quality values obtained by means of auditory examinations thus represent the target values that are to be achieved by instrumental methods.
• Known methods for instrumental speech quality determination are based on a comparison of a reference speech signal with the speech signal to be evaluated.
• the reference speech signal and the speech signal to be evaluated are segmented into short time segments.
• the spectral properties of the two signals are compared in these segments.
• the spectral intensity map calculated in this way for each period of time under consideration can be understood as a series of numerical values in which the number of individual values corresponds to the number of frequency bands used, the numerical values themselves represent the calculated intensity values and a continuous index of the frequency bands describes the sequence of the numerical values.
• the limits of the frequency bands used are kept constant on the frequency axis.
• the calculated intensities of the speech signal to be evaluated and the reference speech signal in each band are compared with one another.
• the difference between the two values, or the similarity of the two resulting spectral intensity images, is the basis for the calculation of a quality value
• a disadvantage of the methods known today in such cases is that when comparing the speech signal to be evaluated with a reference speech signal, differences between the two signal sections in the selected display level flow into the quality characteristic to be calculated, which are not or hardly at all - also perceptible in the auditory test - lead to qualitative impairment.
• Frequency band limitations and spectral deformations of the speech signal to be evaluated e.g. caused by filter properties of the telephone device or the transmission channel
• the object of the invention is to reduce the influence of spectral limitations and deformations of the speech signal to be evaluated and of shifts in spectral short-term maxima before comparing the spectral properties of a signal to be tested with a reference speech signal and calculating a quality value in instrumental methods.
• a spectral weighting function is generated in the invention described here, which is based on medium spectral envelopes, e.g. the average spectral power density, based on the speech signal to be evaluated and the reference speech signal. This also enables the method to be used for non-linear and time-variant transmission.
• the spectral weighting function is calculated from the quotients of the base values of the mean spectral power density of the signal Phi ⁇ (f) to be evaluated and that of the input signal of the transmission system Phi ⁇ (f) in such a way that the weighting function over
• the evaluation function a (f) can weight the weighting function W ⁇ (f) differently over the effective range, in the simplest case it is constant 1.
• the spectral weighting function W ⁇ (f) calculated in this way approximates the mean spectral envelopes of the speech signal and the reference speech signal to be evaluated, so that differences between the two spectral envelopes are only incorporated to a reduced extent in the calculated quality value.
• the spectral weighting function W ⁇ (f) can be applied to the reference speech signal.
• the average spectral power density of the reference speech signal is approximated to the signal to be evaluated (FIG. 2a).
• the spectral weighting function can be applied inverted to the signal to be evaluated. This is equalized and, with regard to its average spectral power density, approximated to the reference speech signal (FIG. 2b).
• Another part of the invention relates to the correction of shifts in short-term spectral maxima caused by the transmission systems.
• the intensity is integrated in frequency bands for each time period.
• the result is a series of intensity values for each spectral representation of a signal section, each individual value representing the intensity in a frequency band.
• the shifts in short-term spectral maxima can lead to deviating calculated intensities in the frequency bands of the reference speech signal and the speech signal to be evaluated.
• variable band limits for calculating the spectral intensity mapping is not only limited to the signal in which the described spectral weighting function W ⁇ (f) is also used, but can also be applied to the other signal and even to both signals, ( see FIGS. 2a and 2b).
• a special exemplary embodiment shows an implementation according to FIG. 3, which is referred to as TOSQA (Telecommunication Objective Speech Quality Assessment). This involves advanced preprocessing of the reference speech signal.
• TOSQA Telecommunication Objective Speech Quality Assessment
• speech pauses are recognized here by means of a speech pause recognizer and do not go into the quality measure.
• the reference speech signal and the speech signal to be evaluated are also filtered with a bandpass 300 ... 3400 Hz and the frequency response of a telephone handset is filtered.
• the spectral power density is integrated in frequency groups, which form the basis for the calculation of the specific loudness.
• the calculated loudness patterns are supplemented by an error evaluation function.
• the calculated quality value is formed from the mean value of the co-correlation coefficients of the specific loudnesses for each short time segment under consideration from the number of evaluated speech segments.

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)
• Compression, Expansion, Code Conversion, And Decoders (AREA)
• Machine Translation (AREA)
• Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)

Applications Claiming Priority (3)

Publications (2)

Family

ID=7879918

Family Applications (1)

Country Status (6)

Families Citing this family (12)

Family Cites Families (6)

• 1998
  • 1998-08-27 DE DE19840548A patent/DE19840548C2/de not_active Expired - Fee Related
• 1999
  • 1999-08-14 CA CA002305652A patent/CA2305652A1/fr not_active Abandoned
  • 1999-08-14 US US09/530,389 patent/US7013266B1/en not_active Expired - Lifetime
  • 1999-08-14 EP EP99942871A patent/EP1048025B1/fr not_active Expired - Lifetime
  • 1999-08-14 AT AT99942871T patent/ATE253765T1/de active
  • 1999-08-14 WO PCT/EP1999/005972 patent/WO2000013173A1/fr active IP Right Grant
  • 1999-08-14 DE DE59907623T patent/DE59907623D1/de not_active Expired - Lifetime

Non-Patent Citations (1)

Also Published As

Similar Documents

Legal Events