EP0993671A1 - Procede de recherche d'un modele de bruit dans des signaux sonores bruites - Google Patents
Procede de recherche d'un modele de bruit dans des signaux sonores bruitesInfo
- Publication number
- EP0993671A1 EP0993671A1 EP98935094A EP98935094A EP0993671A1 EP 0993671 A1 EP0993671 A1 EP 0993671A1 EP 98935094 A EP98935094 A EP 98935094A EP 98935094 A EP98935094 A EP 98935094A EP 0993671 A1 EP0993671 A1 EP 0993671A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- model
- noise
- search
- frames
- energy
- 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 27
- 230000005236 sound signal Effects 0.000 title abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000004364 calculation method Methods 0.000 claims description 18
- 230000003595 spectral effect Effects 0.000 claims description 13
- 238000011161 development Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 3
- 230000003252 repetitive effect Effects 0.000 claims description 2
- 238000002360 preparation method Methods 0.000 claims 1
- 230000015654 memory Effects 0.000 description 12
- 230000029058 respiratory gaseous exchange Effects 0.000 description 9
- 239000000523 sample Substances 0.000 description 6
- 101150052726 DSP2 gene Proteins 0.000 description 5
- 230000003936 working memory Effects 0.000 description 5
- 101150115013 DSP1 gene Proteins 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 102100040489 DNA damage-regulated autophagy modulator protein 2 Human genes 0.000 description 2
- 101000968012 Homo sapiens DNA damage-regulated autophagy modulator protein 2 Proteins 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000010183 spectrum analysis Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000011282 treatment Methods 0.000 description 2
- 102100020800 DNA damage-regulated autophagy modulator protein 1 Human genes 0.000 description 1
- 101000931929 Homo sapiens DNA damage-regulated autophagy modulator protein 1 Proteins 0.000 description 1
- 206010028916 Neologism Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000002542 deteriorative effect Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000001747 exhibiting effect Effects 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000009423 ventilation 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
- G10L21/0216—Noise filtering characterised by the method used for estimating noise
- G10L2021/02168—Noise filtering characterised by the method used for estimating noise the estimation exclusively taking place during speech pauses
Definitions
- the invention relates to improving the intelligibility of voice communications in the presence of noise. It applies more specifically but not exclusively to telephone or radiotelephone or other electronic communications, to voice recognition, etc., whenever the environment of the sound recording is noisy and risks deteriorating perception or recognition of the transmitted voice.
- the noises result from the engines, air conditioning, ventilation of on-board equipment, aerodynamic noises. These noises are picked up by the microphone in which the pilot or a member of the crew speaks.
- the invention proposes a method for searching for a noise model which can be used in particular in noise reduction treatments.
- the noise reduction treatments based on the noise model found make it possible to increase the signal / noise ratio of the transmitted signal, one aim being to deteriorate the intelligibility of the signal as little as possible.
- the denoising and denoising neologisms will be used to speak of operations aimed at removing or reducing noise components present in the signal.
- Denoising can be based as we will see on the permanent search for an ambient noise model, on the digital spectral analysis of this noise, and on the digital reconstruction of a useful signal eliminating as much as possible the modeled noise.
- the invention proposes a method for automatically searching for noise models in noisy sound input signals, in which the input signals are digitized, and these signals are processed from a found model (for example with a view to eliminating the noise corresponding to the model as well as possible), characterized in that the input signals are divided into successive frames of P samples each, and a repetitive search for a noise model is carried out continuously in the signals input themselves, by searching for N successive frames having the expected characteristics of a noise, by storing the corresponding NxP samples to constitute a noise model useful for processing denoising of the input signals, and by repeating the search for find a new noise model and store the new model to replace the previous one or keep the previous model according to the respective characteristics of the d them models.
- the noise model used in particular for denoising is not a known predetermined model or a model chosen from several predetermined models, but it is a model found in the noisy signal itself, which allows not only to adapt denoising to real annoying noise, but also adapt denoising to variations in this noise.
- the noise model is obtained by considering that the signals whose energy is stable (and preferably, as we will see, whose energy is minimum), over a certain duration probably represent noise; the search for a noise model then includes the search for N successive frames whose energies are close to each other (N being between a minimum value N1 and a maximum value N2), the calculation of the average energy of the N successive frames found, and the storage of NxP samples as a new active model if the ratio between this average energy and the average energy of the frames of the previously stored active model is less than a determined replacement threshold.
- the search for N successive frames then comprises at least the following iterative steps: calculation of the energy of a current frame of rank n capable of being added to a model under development already comprising n-1 successive frames; ratio calculation between this energy and the energy of the previous frame of rank n-1 (and preferably that of other previous frames between 1 and n-1); comparison of this ratio with a low threshold less than 1 and a high threshold greater than 1; and decision on the possibility of incorporating the frame of rank n into the model being developed: the frame is not incorporated into the model if the ratio is not between the two thresholds; it is incorporated into the model if the ratio is between the two thresholds. The procedure is repeated on the next current frame of the input signals, with incrementation of n, until the development of the model is stopped.
- the model developed can only be taken into account as an active model if n-1 is already greater than or equal to the minimum N1, because the principle is that a noise model is representative if it has an energy at roughly stable on at least N1 frames.
- the model developed only becomes active in place of the previous model if the ratio between its average energy per frame and the average energy of the previous model does not exceed a predetermined replacement threshold.
- the replacement of a previous model by a new model is inhibited as soon as speech is detected in the noisy signals.
- the presence of speech can indeed be detected by digital signal processing procedures (such as those that can be used in speech recognition).
- FIG. 1 shows a general flowchart of a noise reduction method using the method of the invention
- - Figure 2 shows a typical example of a signal from a noise pickup
- - Figure 3 shows the flow diagram of the steps for finding a noise model in the input signal
- FIG. 4 shows an example of electronic circuit architecture for the implementation of denoising operations using the method according to the invention.
- the processing of the input signals is a denoising processing from the noise model found.
- Other applications can be envisaged (search for whistling or hissing consonants, for example).
- the general principle of the denoising process is based on a permanent and automatic search for a noise model which will be used to process the input signal to denois it.
- This research is done on the signal samples u (t) digitized and stored in an input buffer memory.
- This memory is capable of memorizing all the samples of several frames of the input signal (for example at least 2 frames).
- the noise model sought is made up of a succession of several frames whose energy stability and relative energy level make one think that it is an ambient noise and not a speech signal or a other disturbing noise. We will see later how this automatic search is done.
- the denoising of the input signal u (t) is done from the noise model that is in memory, and more precisely from the spectral characteristics of this model. A Fourier transform and an estimate of average spectral noise density are therefore performed on the stored noise model.
- the denoising operation is preferably done thanks to a digital Wiener filtering on which we will come back in more detail.
- the Wiener filter is parameterized by the spectral characteristics of the recorded noise model and by the spectral characteristics of the signal u (t) to be noise-suppressed.
- the digitized input signal therefore undergoes a Fourier transform and an estimation of spectral density.
- the digital values of the Fourier transform i.e. the input signal represented by its frequency components, are processed by the Wiener filter and the output of the Wiener filter represents, in frequency space, the noisy digital signal, that is to say rid as much as possible of the noise represented by the recorded model.
- the filtered digital signal is used either for the reconstruction of a sound signal in which the ambient noise has been partially eliminated, or for voice recognition.
- the phase of automatic search for a noise model and the permanent updating of this model are crucial steps of the method and are more precisely the subject of the invention.
- the starting postulates for the automatic development of a noise model are as follows:
- the noise that we want to eliminate is the ambient background noise
- noise and speech are superimposed in terms of signal energy, so that a signal containing speech or disturbing noise, including breathing in the microphone, necessarily contains more energy than an ambient noise signal.
- ambient noise is a signal exhibiting a stable minimum energy in the short term.
- short term is meant a few frames, and it will be seen in the practical example given below that the number of frames intended to evaluate the stability of the noise is from 5 to 20.
- the energy must be stable over several frames, fault what we must assume that the signal contains rather speech or noise other than ambient noise. It must be minimal, failing which it is considered that the signal contains respiration or phonetic elements of speech resembling noise but superimposed on ambient noise.
- FIG. 2 represents a typical configuration of the temporal evolution of the energy of a microphone signal at the time of the start of emission of speech, with a phase of breath noise, which goes out for a few tens to hundreds of milliseconds to make room for ambient noise alone, after which a high energy level indicates the presence of speech, to finally return to ambient noise.
- N1 5
- the digital values of all the samples of these N frames are stored.
- This set of NxP samples constitutes the current noise model. It is used in denoising. Analysis of the following frames continues.
- the ambient noise changes slowly, the change will be taken into account since the comparison threshold with the stored model is greater than 1. If it changes more rapidly in the increasing direction, the change may not be taken into account, so it is better to plan from time to time a reset of the search for a noise model. For example, in an aircraft on the ground at a standstill, the ambient noise will be relatively low, and the noise model should not be fixed during the takeoff phase on what it was at a standstill of the fact that a noise model is replaced only by a less energetic model or not much more energetic.
- the reinitialization methods envisaged will be explained below.
- FIG. 3 represents a flow diagram of the operations for automatically searching for an ambient noise model.
- the input signal u (t), sampled at the frequency F ⁇ 1 / T ⁇ and digitized by an analog-digital converter, is stored in a buffer memory capable of storing all the samples of at least 2 frames.
- n The number of the current frame in a search operation for a noise model is designated by n and is counted by a counter as the search is carried out. At the initialization of the search, n is set to 1. This number n will be incremented as a model of several successive frames is developed. When analyzing the current frame n, the model already includes by hypothesis n-1 successive frames meeting the conditions imposed to be part of a model.
- the signal energy of the frame is calculated by summing the squares of the digital values of the samples of the frame. It is kept in memory.
- the ratio between the energies of the two frames is calculated. If this ratio is between two thresholds S and S 'one of which is greater than 1 and the other of which is less than 1, it is considered that the energies of the two frames are close and that the two frames can be part of a noise model.
- the rank n of the current frame is incremented, and an energy calculation of the next frame is carried out in an iterative procedure loop and a comparison with the energy of the previous frame or from previous frames, using thresholds S and S ".
- the first type of comparison consists in comparing only the energy of the frame n to l energy of frame n-1.
- the second type consists in comparing the energy of the frame n to each of the frames 1 to n-1.
- the second way leads to a greater homogeneity of the model but it has the disadvantage of not taking into account sufficiently well the cases where the noise level increases or decreases quickly.
- the energy of the frame of rank n is compared with the energy of the frame of rank n-1 and possibly of other previous frames (not necessarily all of them for that matter).
- N1 5; in this case we abandon the model being developed, and we reset the search at the beginning by giving n to 1;
- n is greater than the minimum number N1.
- the number N2 is chosen so as to limit the computation time in the subsequent operations for estimating the spectral noise density. If n is less than N2, the homogeneous frame is added to the previous ones to help build the noise model, n is incremented and the next frame is analyzed.
- n is equal to N2
- the frame is also added to the previous n-1 homogeneous frames and the model of n homogeneous frames is stored to be used for noise elimination.
- the search for a model is also reset by setting n to 1.
- the previous steps relate to the first model search. But once a model has been stored, it can be replaced at any time by a more recent model.
- the replacement condition is still an energy condition, but this time it relates to the average energy of the model and no longer to the energy of each frame.
- the new model is considered to be better and it is stored in place of the previous one. Otherwise, the new model is rejected and the old one remains in force.
- the threshold SR is preferably slightly greater than 1. If the threshold SR were less than or equal to 1, each time the least energetic homogeneous frames would be stored, which corresponds well to the fact that the ambient noise is considered to be the energy level at below which we never descend. But, we would eliminate any possibility of evolution of the model if the ambient noise started to increase.
- SR threshold was too high above 1, there is a risk of making a poor distinction between ambient noise and other disturbing noises (breathing), or even certain phonemes that sound like noise (whistling or hissing consonants for example). Eliminating noise from a model of noise calibrated on respiration or on whistling or hissing consonants would risk damaging the intelligibility of the noisy signal.
- the threshold SR is approximately 1.5. Above this threshold we will keep the old model; below this threshold we will replace the old model with the new one. In both cases, the search will be reinitialized by recommencing the reading of a first frame of the input signal u (t), and setting n to 1.
- the digital signal processing commonly used in speech detection makes it possible to identify the presence of speech based on the characteristic spectra of periodicity of certain phonemes, in particular the phonemes corresponding to vowels or to voiced consonants.
- This inhibition is to avoid that certain sounds are taken for noise whereas they are useful phonemes, that a noise model based on these sounds is stored and that the suppression of noise after the development of the model. then tends to suppress all similar sounds.
- SR is not much higher than 1.
- Ambient noise can indeed increase significantly and quickly, for example during the acceleration phase of the engines of an airplane or other vehicle, air, land or sea.
- the threshold SR requires that the previous noise model be kept when the average noise energy increases too quickly. If we want to remedy this situation, we can proceed in different ways, but the easiest way is to reset the model periodically by looking for a new model and by imposing it as an active model regardless of the comparison between this model and the model. previously stored.
- the periodicity can be based on the average duration of speech in the envisaged application; for example, the speaking times are on average a few seconds for the crew of an airplane, and the reinitialization can take place with a periodicity of a few seconds.
- the actual denoising processing, carried out from a stored noise model, can be carried out in the following manner, by working on the Fourier transforms of the input signal.
- the Fourier transform of the input signal is carried out frame by frame and provides for each frame P samples in the frequency space, each sample corresponding to a frequency F ⁇ with i varying from 1 to P. These P samples will preferably be processed in a Wiener filter.
- the Wiener filter is a digital filter of P coefficients each corresponding to one of the frequencies FJ ⁇ of the frequency space. Each sample of the input signal in the frequency space is multiplied by the respective coefficient Wj of the filter.
- the set of P samples thus processed constitutes a denoised signal frame in the frequency space. For speech recognition applications, these denoised frames are used directly in the frequency space. For applications where we want to reconstruct a real denoised sound signal, we perform successively an inverse Fourier transform on each frame, a digital-analog conversion, and a smoothing.
- the coefficients Wj of the Wiener filter are calculated from the spectral density of the noisy input signal and the noise spectral density of the stored noise model.
- the spectral density of a frame of the input signal is obtained from the Fourier transform of the noisy input signal. For each frequency, we take the squared module of the sample provided by the Fourier transform, to obtain a value DSj for each frequency F, / !.
- the square module of the P samples is calculated for each frame, and the N square modules corresponding to the same frequency are averaged over the N frames of the noise model
- the Wiener coefficient W, for the frequency F is then
- W, 1 - DB./DS,.
- the sample of rank i of the Fourier transform of an input signal frame is multiplied by W, and the succession of the P samples thus multiplied by P Wiener coefficients constitutes the denoised input frame.
- the implementation of the method according to the invention can be done from non-specialized computers, provided with the necessary calculation programs and receiving the samples of digitized signals as supplied by an analog-digital converter.
- This implementation can also be done using a specialized computer based on digital signal processors, which makes it possible to process a larger number of digital signals more quickly.
- FIG. 4 represents an example of the general architecture of a specialized computer receiving the sound signal to be denoised and providing in real time a denoised sound signal.
- the computer comprises two digital signal processors DSP1 and DSP2 and working memories associated with these processors.
- the noisy sound signals pass through an analog-digital AC / D converter and are stored in parallel in two buffer memories FIF01 and FIF02 (of the "first-in, first-out" type, that is to say first in first out ).
- One of the memories is connected to the processor DSP1, the other to the processor DSP2.
- the DSP1 processor is the master processor and is rather dedicated to finding a noise model. It is therefore programmed to execute at least the following operations: frame energy calculation, energy average calculations, comparison with thresholds, frame rank comparison with N1 and N2, etc. It also calculates spectral energy densities of the noise model.
- This DSP1 processor is coupled to a dynamic working memory DRAM1 in which the sample of current frame is stored during a calculation, the energy of a current frame, the energy of the previous frame or frames, the samples of Fourier transform of the noise model. It is also coupled to a static working memory in which the tables used for the calculation of Fourier transforms are stored, and the comparison thresholds S and SR.
- the DSP2 processor is dedicated rather to the calculation of Fourier transforms of the signal to be noise-suppressed, to the calculation of the spectral density of this signal, to the calculation of the Wiener coefficients, to the Wiener filtering, and to the inverse Fourier transform if the latter must be performed.
- the DSP2 processor is coupled to a dynamic working memory DRAM2 and a static working memory SRAM2.
- the DRAM2 memory stores samples of current frame, Fourier transform calculation results, signal energy density calculation results, calculated Wiener coefficients, etc.
- the SRAM2 memory stores tables used in particular for computation of Fourier transforms.
- the denoised sound signal samples calculated by the processor DSP2 are transmitted, through a circulating buffer memory FIFO3, to a digital analog converter CN / A, and to a smoothing circuit which reconstructs the denoised sound signal in analog form.
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (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)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Soundproofing, Sound Blocking, And Sound Damping (AREA)
- Noise Elimination (AREA)
Abstract
Description
Claims
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
FR9708509A FR2765715B1 (fr) | 1997-07-04 | 1997-07-04 | Procede de recherche d'un modele de bruit dans des signaux sonores bruites |
FR9708509 | 1997-07-04 | ||
PCT/FR1998/001428 WO1999001862A1 (fr) | 1997-07-04 | 1998-07-03 | Procede de recherche d'un modele de bruit dans des signaux sonores bruites |
Publications (2)
Publication Number | Publication Date |
---|---|
EP0993671A1 true EP0993671A1 (fr) | 2000-04-19 |
EP0993671B1 EP0993671B1 (fr) | 2002-06-12 |
Family
ID=9508879
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP98935094A Expired - Lifetime EP0993671B1 (fr) | 1997-07-04 | 1998-07-03 | Procede de recherche d'un modele de bruit dans des signaux sonores bruites |
Country Status (6)
Country | Link |
---|---|
US (1) | US6438513B1 (fr) |
EP (1) | EP0993671B1 (fr) |
JP (1) | JP4338226B2 (fr) |
DE (1) | DE69806006T2 (fr) |
FR (1) | FR2765715B1 (fr) |
WO (1) | WO1999001862A1 (fr) |
Families Citing this family (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6633842B1 (en) * | 1999-10-22 | 2003-10-14 | Texas Instruments Incorporated | Speech recognition front-end feature extraction for noisy speech |
EP1104925A1 (fr) * | 1999-12-03 | 2001-06-06 | Siemens Aktiengesellschaft | Procédé de traitement de la parole par soustraction d'une fonction du bruit |
EP1152399A1 (fr) * | 2000-05-04 | 2001-11-07 | Faculte Polytechniquede Mons | Traitement en sous bandes de signal de parole par réseaux de neurones |
FR2808917B1 (fr) * | 2000-05-09 | 2003-12-12 | Thomson Csf | Procede et dispositif de reconnaissance vocale dans des environnements a niveau de bruit fluctuant |
US7072833B2 (en) * | 2000-06-02 | 2006-07-04 | Canon Kabushiki Kaisha | Speech processing system |
US6954745B2 (en) * | 2000-06-02 | 2005-10-11 | Canon Kabushiki Kaisha | Signal processing system |
US7010483B2 (en) * | 2000-06-02 | 2006-03-07 | Canon Kabushiki Kaisha | Speech processing system |
US7035790B2 (en) * | 2000-06-02 | 2006-04-25 | Canon Kabushiki Kaisha | Speech processing system |
US20020026253A1 (en) * | 2000-06-02 | 2002-02-28 | Rajan Jebu Jacob | Speech processing apparatus |
EP1170728A1 (fr) * | 2000-07-05 | 2002-01-09 | Alcatel | Dispositif de réduction adaptive du bruit dans des signaux de parole |
BR0207553A (pt) * | 2001-02-23 | 2004-09-14 | Popcatcher Inc | Método e dispositivo para busca e gravação de sinais de mìdia |
US7062442B2 (en) * | 2001-02-23 | 2006-06-13 | Popcatcher Ab | Method and arrangement for search and recording of media signals |
GB2380644A (en) * | 2001-06-07 | 2003-04-09 | Canon Kk | Speech detection |
FR2842064B1 (fr) * | 2002-07-02 | 2004-12-03 | Thales Sa | Systeme de spatialisation de sources sonores a performances ameliorees |
SE524162C2 (sv) * | 2002-08-23 | 2004-07-06 | Rickard Berg | Förfarande för att behandla signaler |
WO2004109661A1 (fr) * | 2003-06-05 | 2004-12-16 | Matsushita Electric Industrial Co., Ltd. | Appareil et procede de reglage de la qualite sonore |
EP1494040A1 (fr) * | 2003-06-30 | 2005-01-05 | Sulzer Markets and Technology AG | Méthode de compensation de bruit de quantification et utilisation de la méthode |
US8718298B2 (en) * | 2003-12-19 | 2014-05-06 | Lear Corporation | NVH dependent parallel compression processing for automotive audio systems |
US7813921B2 (en) * | 2004-03-31 | 2010-10-12 | Pioneer Corporation | Speech recognition device and speech recognition method |
US7139701B2 (en) * | 2004-06-30 | 2006-11-21 | Motorola, Inc. | Method for detecting and attenuating inhalation noise in a communication system |
JP5068653B2 (ja) * | 2004-09-16 | 2012-11-07 | フランス・テレコム | 雑音のある音声信号を処理する方法および該方法を実行する装置 |
JP5724361B2 (ja) * | 2010-12-17 | 2015-05-27 | 富士通株式会社 | 音声認識装置、音声認識方法および音声認識プログラム |
CN108364657B (zh) | 2013-07-16 | 2020-10-30 | 超清编解码有限公司 | 处理丢失帧的方法和解码器 |
US9633669B2 (en) * | 2013-09-03 | 2017-04-25 | Amazon Technologies, Inc. | Smart circular audio buffer |
DE102013111784B4 (de) * | 2013-10-25 | 2019-11-14 | Intel IP Corporation | Audioverarbeitungsvorrichtungen und audioverarbeitungsverfahren |
CN106683681B (zh) | 2014-06-25 | 2020-09-25 | 华为技术有限公司 | 处理丢失帧的方法和装置 |
EP3248191B1 (fr) * | 2015-01-20 | 2021-09-29 | Dolby Laboratories Licensing Corporation | Modélisation et réduction de bruit de systèmes de propulsion de drone |
CN105991900B (zh) * | 2015-02-05 | 2019-08-09 | 扬智科技股份有限公司 | 噪声检测方法和去噪方法 |
CN106067847B (zh) * | 2016-05-25 | 2019-10-22 | 腾讯科技(深圳)有限公司 | 一种语音数据传输方法及装置 |
CN109087659A (zh) * | 2018-08-03 | 2018-12-25 | 三星电子(中国)研发中心 | 音频优化方法及设备 |
Family Cites Families (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4630304A (en) * | 1985-07-01 | 1986-12-16 | Motorola, Inc. | Automatic background noise estimator for a noise suppression system |
US5029118A (en) * | 1985-12-04 | 1991-07-02 | Nissan Motor Co. Ltd. | Periodic noise canceling system and method |
FR2677828B1 (fr) | 1991-06-14 | 1993-08-20 | Sextant Avionique | Procede de detection d'un signal utile bruite. |
FR2697101B1 (fr) | 1992-10-21 | 1994-11-25 | Sextant Avionique | Procédé de détection de la parole. |
FR2704111B1 (fr) | 1993-04-16 | 1995-05-24 | Sextant Avionique | Procédé de détection énergétique de signaux noyés dans du bruit. |
US5521851A (en) * | 1993-04-26 | 1996-05-28 | Nihon Kohden Corporation | Noise reduction method and apparatus |
WO1995002288A1 (fr) * | 1993-07-07 | 1995-01-19 | Picturetel Corporation | Reduction de bruits de fond pour l'amelioration de la qualite de voix |
JPH07193548A (ja) * | 1993-12-25 | 1995-07-28 | Sony Corp | 雑音低減処理方法 |
JP3453898B2 (ja) * | 1995-02-17 | 2003-10-06 | ソニー株式会社 | 音声信号の雑音低減方法及び装置 |
JP2685031B2 (ja) * | 1995-06-30 | 1997-12-03 | 日本電気株式会社 | 雑音消去方法及び雑音消去装置 |
US5659622A (en) * | 1995-11-13 | 1997-08-19 | Motorola, Inc. | Method and apparatus for suppressing noise in a communication system |
FR2744871B1 (fr) | 1996-02-13 | 1998-03-06 | Sextant Avionique | Systeme de spatialisation sonore, et procede de personnalisation pour sa mise en oeuvre |
US5937381A (en) * | 1996-04-10 | 1999-08-10 | Itt Defense, Inc. | System for voice verification of telephone transactions |
US6144937A (en) * | 1997-07-23 | 2000-11-07 | Texas Instruments Incorporated | Noise suppression of speech by signal processing including applying a transform to time domain input sequences of digital signals representing audio information |
TW333610B (en) * | 1997-10-16 | 1998-06-11 | Winbond Electronics Corp | The phonetic detecting apparatus and its detecting method |
US6216103B1 (en) * | 1997-10-20 | 2001-04-10 | Sony Corporation | Method for implementing a speech recognition system to determine speech endpoints during conditions with background noise |
US6182018B1 (en) * | 1998-08-25 | 2001-01-30 | Ford Global Technologies, Inc. | Method and apparatus for identifying sound in a composite sound signal |
US6188981B1 (en) * | 1998-09-18 | 2001-02-13 | Conexant Systems, Inc. | Method and apparatus for detecting voice activity in a speech signal |
US6108610A (en) * | 1998-10-13 | 2000-08-22 | Noise Cancellation Technologies, Inc. | Method and system for updating noise estimates during pauses in an information signal |
US6289309B1 (en) * | 1998-12-16 | 2001-09-11 | Sarnoff Corporation | Noise spectrum tracking for speech enhancement |
-
1997
- 1997-07-04 FR FR9708509A patent/FR2765715B1/fr not_active Expired - Fee Related
-
1998
- 1998-07-03 WO PCT/FR1998/001428 patent/WO1999001862A1/fr active IP Right Grant
- 1998-07-03 US US09/446,886 patent/US6438513B1/en not_active Expired - Lifetime
- 1998-07-03 EP EP98935094A patent/EP0993671B1/fr not_active Expired - Lifetime
- 1998-07-03 JP JP50654799A patent/JP4338226B2/ja not_active Expired - Fee Related
- 1998-07-03 DE DE69806006T patent/DE69806006T2/de not_active Expired - Fee Related
Non-Patent Citations (1)
Title |
---|
See references of WO9901862A1 * |
Also Published As
Publication number | Publication date |
---|---|
DE69806006D1 (de) | 2002-07-18 |
EP0993671B1 (fr) | 2002-06-12 |
US6438513B1 (en) | 2002-08-20 |
FR2765715B1 (fr) | 1999-09-17 |
DE69806006T2 (de) | 2002-12-19 |
JP4338226B2 (ja) | 2009-10-07 |
FR2765715A1 (fr) | 1999-01-08 |
JP2002513479A (ja) | 2002-05-08 |
WO1999001862A1 (fr) | 1999-01-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP0993671B1 (fr) | Procede de recherche d'un modele de bruit dans des signaux sonores bruites | |
EP0918317B1 (fr) | Procédé de filtrage fréquentiel appliqué au débruitage de signaux sonores mettant en oeuvre un filtre de Wiener | |
EP1789956B1 (fr) | Procede de traitement d'un signal sonore bruite et dispositif pour la mise en oeuvre du procede | |
EP1154405B1 (fr) | Procédé et dispositif de reconnaissance vocale dans des environnements a niveau de bruit fluctuant | |
EP0594480B1 (fr) | Procédé de détection de la parole | |
EP2415047B1 (fr) | Classification du bruit de fond contenu dans un signal sonore | |
EP0932964B1 (fr) | Procede et dispositif d'egalisation aveugle des effets d'un canal de transmission sur un signal de parole numerique | |
EP2772916B1 (fr) | Procédé de débruitage d'un signal audio par un algorithme à gain spectral variable à dureté modulable dynamiquement | |
WO2010119216A1 (fr) | Procede et dispositif d'evaluation objective de la qualite vocale d'un signal de parole prenant en compte la classification du bruit de fond contenu dans le signal | |
WO2003048711A2 (fr) | System de detection de parole dans un signal audio en environnement bruite | |
EP1131813B1 (fr) | Procede de reconnaissance vocale dans un signal acoustique bruite et systeme mettant en oeuvre ce procede | |
EP1152399A1 (fr) | Traitement en sous bandes de signal de parole par réseaux de neurones | |
EP0534837B1 (fr) | Procédé de traitement de la parole en présence de bruits acoustiques utilisant la sous traction spectrale non-linéaire et les modèles de Markov cachés | |
WO1999014739A1 (fr) | Procede de debruitage d'un signal de parole numerique | |
WO1999014744A1 (fr) | Procede de conditionnement d'un signal de parole numerique | |
WO1999027523A1 (fr) | Procede de reconstruction, apres debruitage, de signaux sonores | |
FR2751776A1 (fr) | Procede d'extraction de la frequence fondamentale d'un signal de parole | |
FR2846136A1 (fr) | Dispositif d'expension/compression de l'enveloppe d'amplitude du signal de parole | |
WO2002093553A1 (fr) | Estimation de periodes fondamentales de sources concurrentes multiples notamment de son |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
17P | Request for examination filed |
Effective date: 20000105 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): DE FR GB NL |
|
17Q | First examination report despatched |
Effective date: 20000921 |
|
RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: THALES AVIONICS S.A. |
|
GRAG | Despatch of communication of intention to grant |
Free format text: ORIGINAL CODE: EPIDOS AGRA |
|
RIC1 | Information provided on ipc code assigned before grant |
Free format text: 7G 10L 21/02 A |
|
GRAG | Despatch of communication of intention to grant |
Free format text: ORIGINAL CODE: EPIDOS AGRA |
|
GRAH | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOS IGRA |
|
GRAH | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOS IGRA |
|
GRAA | (expected) grant |
Free format text: ORIGINAL CODE: 0009210 |
|
AK | Designated contracting states |
Kind code of ref document: B1 Designated state(s): DE FR GB NL |
|
REG | Reference to a national code |
Ref country code: GB Ref legal event code: FG4D Free format text: NOT ENGLISH |
|
REF | Corresponds to: |
Ref document number: 69806006 Country of ref document: DE Date of ref document: 20020718 |
|
GBT | Gb: translation of ep patent filed (gb section 77(6)(a)/1977) |
Effective date: 20020813 |
|
PLBE | No opposition filed within time limit |
Free format text: ORIGINAL CODE: 0009261 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT |
|
26N | No opposition filed |
Effective date: 20030313 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: NL Payment date: 20090705 Year of fee payment: 12 Ref country code: GB Payment date: 20090701 Year of fee payment: 12 Ref country code: DE Payment date: 20090626 Year of fee payment: 12 |
|
REG | Reference to a national code |
Ref country code: NL Ref legal event code: V1 Effective date: 20110201 |
|
GBPC | Gb: european patent ceased through non-payment of renewal fee |
Effective date: 20100703 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: DE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20110201 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R119 Ref document number: 69806006 Country of ref document: DE Effective date: 20110201 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: NL Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20110201 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: GB Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20100703 |
|
REG | Reference to a national code |
Ref country code: FR Ref legal event code: PLFP Year of fee payment: 19 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: FR Payment date: 20160628 Year of fee payment: 19 |
|
REG | Reference to a national code |
Ref country code: FR Ref legal event code: ST Effective date: 20180330 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: FR Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20170731 |