Session ThAA Noise Mitigation, Speech Enhancement II
`5/24/22, 12:40 PM
`The Wayback Machine - https://web.archive.org/web/19991021233509/http://www.wcl2.ee.upatras.gr:80/eurt…
`
`Session ThAA Noise Mitigation, Speech
`Enhancement II
`Chairperson Bayya Yegnanarayana IIT MADRAS, India
`
` Home
`
`NOISY SPEECH ENHANCEMENT BY FUSION OF AUDITORY
`AND VISUAL INFORMATION: A STUDY OF VOWEL
`TRANSITIONS
`
`Authors: L. Girin, G. Feng & J.L. Schwartz
`
`Institut de la Communication Parlée, UPRESA 5009 INPG/ENSERG/Université Stendhal B.P. 25, 38040
`GRENOBLE CEDEX 09, FRANCE E-mail : girin@icp.grenet.fr
`
`Volume 5 pages 2555 - 2558
`
`ABSTRACT
`
`This paper deals with a noisy speech enhancement technique based on the fusion of auditory and visual
`information. We first present the global structure of the system, and then we focus on the tool we used to melt
`both sources of information. The whole noise reduction system is implemented in the context of vowel
`transitions corrupted with white noise. A complete evaluation of the system in this context is presented,
`including distance measures, gaussian classification scores, and a perceptive test. The results are very promising.
`
`SPECTRAL SUBTRACTION USING A NON-CRITICALLY
`DECIMATED DISCRETE WAVELET TRANSFORM
`
`Authors: Andreas Engelsberg and Thomas Gulzow
`
`Institute for Network and System Theory, Technical Department, Kiel University, Kaiserstrasse 2, D-
`24143 Kiel / Germany, E-mail: ae@techfak.uni-kiel.de and tg@techfak.uni-kiel.de
`
`Volume 5 pages 2559 - 2562
`
`ABSTRACT
`
`The method of spectral subtraction has become very popular in speech enhancement. It is performed by
`modifying the spectral amplitudes of the disturbed signal. The spectral analysis of the signal is usually done by a
`Discrete Fourier Transformation (DFT). We propose a spectral transformation with nonuniform bandwidth to
`take into account the characteristics of the human ear. The spectral analysis and synthesis is performed by a non-
`https://web.archive.org/web/19991021233509/http://www.wcl2.ee.upatras.gr:80/eurthaa.html
`1/9
`
`Page 1 of 9
`
`GOOGLE EXHIBIT 1012
`
`

`

`Session ThAA Noise Mitigation, Speech Enhancement II
`5/24/22, 12:40 PM
`critically decimated discrete wavelet transform. Critical subsampling is not performed to avoid errors due to
`aliasing. A significant drawback of spectral-subtraction methods are tonal residual noises in speech pauses with
`unnatural sound. The application of the proposed wavelet transform results in reduced residual noise with
`subjectively more comfortable sound.
`
`BAYESIAN AFFINE TRANSFORMATION OF HMM
`PARAMETERS FOR INSTANTANEOUS AND SUPERVISED
`ADAPTATION IN TELEPHONE SPEECH RECOGNITION
`
`Authors: Jen-Tzung Chien (a), Hsiao-Chuan Wang (a) and Chin-Hui Lee (b)
`
`(a) Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan (b)
`Multimedia Communications Research Lab, Bell Laboratories, Murray Hill, USA
`chien@speech.ee.nthu.edu.tw hcwang@ee.nthu.edu.tw chl@research.bell-labs.com
`
`Volume 5 pages 2563 - 2566
`
`ABSTRACT
`
`This paper proposes a Bayesian affine transformation of hidden Markov model (HMM) parameters for reducing
`the acoustic mismatch problem in telephone speech recognition. Our purpose is to transform the existing HMM
`parameters into its new version of specific telephone environment using affine function so as to improve the
`recognition rate. The maximum a posteriori (MAP) estimation which merges the prior statistics into
`transformation is applied for estimating the transformation parameters. Experiments demonstrate that the
`proposed Bayesian affine transformation is effective for instantaneous adaptation and supervised adaptation in
`telephone speech recognition. Model transformation using MAP estimation performs better than that using
`maximum-likelihood (ML) estimation.
`
`INTEGRATED BIAS REMOVAL TECHNIQUES FOR ROBUST
`SPEECH RECOGNITION \Lambda
`
`Authors: Craig Lawrence and Mazin Rahim (1)
`
`University of Maryland, College Park, MD 20742 (1)AT&T; Labs-Research, Murray Hill, NJ 07974
`
`Volume 5 pages 2567 - 2570
`
`ABSTRACT
`
`In this paper, we present a family of maximum likelihood (ML) techniques that aim at reducing an acoustic
`mismatch between the training and testing conditions of hid- den Markov model (HMM)-based automatic
`speech recognition (ASR) systems. We propose a codebook-based stochastic matching (CBSM) approach for
`bias removal both at the feature level and at the model level. CBSM associates each bias with an ensemble of
`HMM mixture components that share similar acoustic characteristics. It is integrated with hierarchical signal
`bias removal (HSBR) and further extended to accommodate for N-best candidates. Experimental results on
`connected digits, recorded over a cellular network, shows that the proposed system reduces both the word and
`string error rates by about 36% and 31%, respectively, over a baseline system not incorporating bias removal.
`
`https://web.archive.org/web/19991021233509/http://www.wcl2.ee.upatras.gr:80/eurthaa.html
`
`2/9
`
`Page 2 of 9
`
`

`

`5/24/22, 12:40 PM
`
`ACOUSTIC FRONT ENDS FOR SPEAKER-INDEPENDENT DIGIT
`RECOGNITION IN CAR ENVIRONMENTS
`
`Session ThAA Noise Mitigation, Speech Enhancement II
`
`Authors: D. Langmann, A. Fischer, F. Wuppermann, R. Haeb-Umbach, T. Eisele
`
`Philips GmbH Forschungslaboratorien Aachen P.O. Box 50 01 45 D-52085 Aachen Germany Email:
`flangmann,afischer,wupper,haeb,eiseleg@pfa.research.philips.com
`
`Volume 5 pages 2571 - 2574
`
`ABSTRACT
`
`This paper describes speaker-independent speech recognition experiments concerning acoustic front end
`processing on a speech database that was recorded in 3 different cars. We investigate different feature analysis
`approaches (mel-filter bank, mel-cepstrum, perceptually linear predictive coding) and present results with noise
`compensation techniques based on spectral subtraction. Although the methods employed lead to considerable
`error rate reduction the error analysis shows that low signal-to-noise ratios are still a problem.
`
`SIGNAL BIAS REMOVAL USING THE MULTI-PATH
`STOCHASTIC EQUALIZATION TECHNIQUE
`
`Authors: Lionel Delphin-Poulat and Chafic Mokbel
`
`FT.CNET/DIH/RCP 2 av. Pierre Marzin, 22307 Lannion cedex, France. Tel. +33 2 96 05 13 47 FAX: +33 2
`96 05 35 30 e-mail : delphinp@lannion.cnet.fr
`
`Volume 5 pages 2575 - 2578
`
`ABSTRACT
`
`We propose using Hidden Markov Models (HMMs) associated with the cepstrum coefficients as a speech signal
`model in order to perform equalization or noise removal. The MUlti-path Stochastic Equalization (MUSE)
`framework allows one to process data at the frame level: it is an on-line adaptation of the model. More precisely,
`we apply this technique to perform bias removal in the cepstral domain in order to increase the robustness of
`automatic speech recognizers. Recognition experiments on two databases recorded on both PSN and GSM
`networks show the efficiency of the proposed method.
`
`SUBBAND ECHO CANCELLATION IN AUTOMATIC SPEECH
`DIALOG SYSTEMS
`
`Authors: Andrej Miksic and Bogomir Horvat
`
`Laboratory for Digital Signal Processing Faculty of Electrical Engineering and Computer Science
`University of Maribor, Smetanova 17, 2000 Maribor, Slovenia Tel. +386 62 221112, E-mail:
`andrej.miksic@uni-mb.si
`
`https://web.archive.org/web/19991021233509/http://www.wcl2.ee.upatras.gr:80/eurthaa.html
`
`3/9
`
`Page 3 of 9
`
`

`

`5/24/22, 12:40 PM
`Volume 5 pages 2579 - 2582
`
`ABSTRACT
`
`Session ThAA Noise Mitigation, Speech Enhancement II
`
`Echo cancellation has been most widely studied for hands-free telephony and for cancelling line echos in
`telephone central offices. The problem of echo cancelling in speech dialog systems is similar, however it has
`some specific requirements. In this contribution, a subband echo cancellation structure is proposed which can be
`integrated in the feature extraction part of a recognizer. A NLMS gradient-based adaptation is performed in
`frequency subbands that can either be derived directly from FFT analysis of input speech signal, or by using a
`proposed reduced-subband approach where the number of subbands is reduced in order to lessen the aliasing
`effect of the FFT. A double-talk detector is proposed based on the estimated error function for decision on
`stopping the adaptation. Finally, a new approach of combining echo cancellation and noise reduction is
`proposed.
`
`Speech Enhancement via Energy Separation
`
`Authors: Hesham Tolba and Douglas O'Shaughnessy
`
`Institut National de la Recherche Scientifique, INRS-Telecommunications, Quebec, Canada. E-mail:
`tolba@inrs-telecom.uquebec.ca and dougo@inrs-telecom.uquebec.ca.
`
`Volume 5 pages 2583 - 2586
`
`ABSTRACT
`
`This work presents a novel technique to enhance speech signals in the presence of interfering noise. In this
`paper, the amplitude and frequency (AM- FM) modulation model [7] and a multi-band analysis scheme [5] are
`applied to extract the speech signal parameters. The enhancement process is performed using a time-warping
`function B(n) that is used to warp the speech signal. B(n) is extracted from the speech signal using the Smoothed
`Energy Operator Separation Algorithm (SEOSA) [4]. This warping is capable of increasing the SNR of the high
`frequency harmonics of a voiced signal by forcing the the quasiperiodic nature of the voiced component to be
`more periodic, and consequently is useful for extracting more robust parameters of the signal in the presence of
`noise.
`
`A Method of Signal Extraction from Noisy Signal
`
`Authors: Masashi UNOKI and Masato AKAGI
`
`unoki@jaist.ac.jp akagi@jaist.ac.jp School of Information Science, Japan Advanced Institute of Science
`and Technology 1-1 Asahidai, Tatsunokuchi, Ishikawa 923-12, Japan
`
`Volume 5 pages 2587 - 2590
`
`ABSTRACT
`
`This paper presents a method of extracting the desired signal from a noise-added signal as a model of acoustic
`source segregation. Using physical constraints related to the four regularities proposed by Bregman, the
`proposed method can solve the problem of segregating two acoustic sources. Two simulations were carried out
`using the following signals: (a) a noise-added AM complex tone and (b) a noisy synthetic vowel. It was shown
`
`https://web.archive.org/web/19991021233509/http://www.wcl2.ee.upatras.gr:80/eurthaa.html
`
`4/9
`
`Page 4 of 9
`
`

`

`Session ThAA Noise Mitigation, Speech Enhancement II
`5/24/22, 12:40 PM
`that the proposed method can extract the desired AM complex tone from noise- added AM complex tone in
`which signal and noise exist in the same frequency region. The SD was reduced an average of about 20 dB. It
`was also shown that the proposed method can extract a speech signal from noisy speech.
`
`MULTI-CHANNEL NOISE REDUCTION USING WAVELET
`FILTER BANK
`
`Authors: SIKA Jiri - DAVIDEK Vratislav
`
`Faculty of Electrical Engineering Czech Technical University Prague, Czech Republic. Tel. +420 2
`24352291, FAX: +420 2 24310784 , E-mail: sika@feld.cvut.cz
`
`Volume 5 pages 2591 - 2594
`
`ABSTRACT
`
`This paper deals with the problem of estimation of a speech signal corrupted by an additive noise when
`observations from two microphones are available. The basic method for noise reduction using the coherence
`function is modified by using wavelets. The both observations are splitted by filter bank in five narrow bands
`through the whole used bandwidth (0...4kHz). The coherence functions are then computed for each band and the
`output speech estimation is reconstructed.
`
`SPEECH SIGNAL DETECTION IN NOISY ENVIRONEMENT
`USING A LOCAL ENTROPIC CRITERION
`
`Authors: I. Abdallah, S. Montrésor and M. Baudry
`
`Laboratoire d'Informatique de l'Université du Maine Email : imad@lium.univ-lemans.fr
`
`Volume 5 pages 2595 - 2598
`
`ABSTRACT
`
`This paper describes an original method for speech/non-speech detection in adverse conditions. Firstly, we
`define a time-dependent function called Local Entropic Criterion [1] based on Shannon's entropy [2]. Then we
`present the detection algorithm and show that at Signal to Noise Ratio (SNR) above 5 dB, it offers a
`segmentation comparable to the one obtained in clean conditions. We finally, describe how at very low SNR ( <
`0 dB) , it permits to detect speech units masked by noise.
`
`A New Algorithm for Robust Speech Recognition: The Delta Vector
`Taylor Series Approach
`
`Authors: Pedro J. Moreno and Brian Eberman
`
`https://web.archive.org/web/19991021233509/http://www.wcl2.ee.upatras.gr:80/eurthaa.html
`
`5/9
`
`Page 5 of 9
`
`

`

`5/24/22, 12:40 PM
`Session ThAA Noise Mitigation, Speech Enhancement II
`email: pjm@crl.dec.com, bse@crl.dec.com Digital Equipment Corporation Cambridge Research
`Laboratory
`
`Volume 5 pages 2599 - 2602
`
`ABSTRACT
`
`In this paper we present a new model-based compensation technique called Delta Vector Taylor Series (DVTS).
`This new technique is an extension and improvement over the Vector Taylor Series (VTS) approach [7] that
`addresses several of its limitations. In particular, we present a new statistical representation for the distribution
`of clean speech feature vectors based on a weighted vector codebook. This change to the underlying probability
`density function (PDF) allows us to produce more accurate and stable solutions for our algorithm. The algorithm
`is also presented in a EM-MAP framework where some the environmental parameters are treated as random
`variables with known PDF's. Finally, we explore a new compensation approach based on the use of convex
`hulls. We evaluate our algorithm in a phonetic classification task on the TIMIT [5] database and also in a small
`vocabulary size speech recognition database. In both databases artificial and natural noise is injected at several
`signal to noise ratios (SNR). The algorithm achieves matched performance at all SNR's above 10 dB.
`
`ROBUST ENHANCEMENT OF REVERBERANT SPEECH USING
`ITERATIVE NOISE REMOVAL
`
`Authors: David Cole (d.cole@qut.edu.au) Miles Moody (m.moody@qut.edu.au) Sridha
`Sridharan (s.sridharan@qut.edu.au)
`
`Speech Research Lab, Signal Processing Research Centre School of Electrical and Electronic Systems
`Engineering Queensland University ofTechnology GPO Box 2434 Brisbane, Australia
`
`Volume 5 pages 2603 - 2606
`
`ABSTRACT
`
`We suggest a new technique for the enhancement ofsingle channel reverberant speech. Previous methods have
`used either waveform deconvolution or modulation envelope deconvolution. Waveform deconvolution requires
`calculation of an inverse room response, and is impractical due to variation with source or receiver movement.
`Modulation envelope deconvolution has been claimed to be position independent, but our research indicates that
`envelope restoration in fact degrades intelligibility of the speech. Our method uses the observation that the
`smoothed segmental spectral magnitude of the room response is less variable with position. This is used to
`estimate the reverberant component of the signal, which is removed iteratively using conventional noise
`reduction algorithms. The enhanced output is not perceptibly affected by positional changes.
`
`A NETWORK SPEECH ECHO CANCELLER WITH COMFORT
`NOISE
`
`Authors: D.J.Jones*, S.D.Watson* ,K.G.Evans*, B.M.G.Cheetham* and R.A.Reeves#.
`
`*Department of Electrical Engineering, The University of Liverpool, Liverpool, L69 3BX, UK. #BT
`Laboratories, Martlesham Heath, Ipswich, IP5 3RE. Tel: +44 (0)151 708-7724 E-mail: davej@liv.ac.uk
`
`https://web.archive.org/web/19991021233509/http://www.wcl2.ee.upatras.gr:80/eurthaa.html
`
`6/9
`
`Page 6 of 9
`
`

`

`5/24/22, 12:40 PM
`Volume 5 pages 2607 - 2610
`
`ABSTRACT
`
`Session ThAA Noise Mitigation, Speech Enhancement II
`
`This paper describes a proposed comfort noise system for a network echo canceller. In this system, any residual
`echo is suppressed using a single threshold centre-clipper, but instead of transmitting silence to the far-end of the
`network, a synthetic version of the background sounds is sent. This masks any 'noise modulation' or 'noise
`pumping' that may otherwise occur. The background sounds are characterised using linear prediction. Periods
`when only background sounds are present are identified by a modified GSM Voice Activity Detector (VAD).
`Informal listening tests have shown that this 'synthetic background' is preferable to the transmission of silence or
`pseudo-random noise that is not spectrally shaped to match the original background.
`
`A NEW METRIC FOR SELECTING SUB-BAND PROCESSING IN
`ADAPTIVE SPEECH ENHANCEMENT SYSTEMS
`
`Authors: Amir Hussain, Douglas R. Campbell and Thomas J. Moir
`
`Department of Electronic Engineering and Physics, University of Paisley, High St., Paisley PA1 2BE,
`Scotland U.K. Corresponding author's email: huss_ee0@paisley.ac.uk
`
`Volume 5 pages 2611 - 2614
`
`ABSTRACT
`
`A multi-microphone adaptive speech enhancement system employing diverse sub-band processing is presented.
`A new robust metric is developed, which is capable of real-time implementation, in order to automatically select
`the best form of processing within each sub-band. It is based on an adaptively estimated inter-channel
`Magnitude Squared Coherence (MSC) relationship, which is used to detect the level of correlation between in-
`band signals from multiple sensors during noise-alone periods in intermittent speech. This paper reports recent
`results of comparative experiments with simulated anechoic data extended to include simulated reverberant data.
`The results demonstrate that the method is capable of significantly outperforming conventional noise
`cancellation schemes.
`
`ESTIMATION OF LPC CEPSTRUM VECTOR OF SPEECH
`CONTAMINATED BY ADDITIVE NOISE AND ITS APPLICATION
`TO SPEECH ENHANCEMENT
`
`Authors: Hidefumi KOBATAKE and Hideta SUZUKI
`
`Graduate School of Bio-Applications and Systems Engineering Tokyo University of Agriculture and
`Technology Koganei, Tokyo 184, JAPAN Tel. +81 423 88 7147, FAX: +81 423 85 5395, E-mail:
`kobatake@cc.tuat.ac.jp
`
`Volume 5 pages 2615 - 2618
`
`ABSTRACT
`
`https://web.archive.org/web/19991021233509/http://www.wcl2.ee.upatras.gr:80/eurthaa.html
`
`7/9
`
`Page 7 of 9
`
`

`

`Session ThAA Noise Mitigation, Speech Enhancement II
`5/24/22, 12:40 PM
`This paper presents a new method for speech enhancement. It is well known that Wiener filtering is effective in
`reducing additive noises and the proposed method is based on it. This paper focuses on the design of Wiener
`filter, where we place emphasis on the recovery of original formant characteristics and the smooth transition of
`speech spectrum. Transformation method of LPC cepstrum vector extracted from noisy speech to reduce noise
`effects is given, which gives an estimated LPC cepstrum vector of original speech. Sharpening of formant peaks
`and eliminating false spectral peaks are necessary for high quality speech restoration and they are realized by the
`proposed method. Experiments of noise reduction have been performed, whose results show the effectiveness of
`the proposed method.
`
`MULTI-BAND AND ADAPTATION APPROACHES TO ROBUST
`SPEECH RECOGNITION
`
`Authors: Sangita Tibrewala (1) and Hynek Hermansky (1),(2)
`
`(1) Oregon Graduate Institute of Science and Technology, Portland, Oregon, USA. (2) International
`Computer Science Institute, Berkeley, California, USA. Email: sangita,hynek@ee.ogi.edu
`
`Volume 5 pages 2619 - 2622
`
`ABSTRACT
`
`In this paper we present two approaches to deal with degradation of automatic speech recognizers due to
`acoustic mismatch in training and testing environments. The first approach is based on the multi-band approach
`to automatic speech recognition (ASR). This approach is shown to be inherently robust to frequency selective
`degradation. In the second approach, we present a conceptually simple unsupervised feature adaptation
`technique, based on recursive estimation of means and variances of the cepstral parameters to compensate for
`the noise effects. Both techniques yield significant reduction in error rates.
`
`NON-QUADRATIC CRITERION ALGORITHMS FOR SPEECH
`ENHANCFNT
`Authors: Enrique Masgrau, Eduardo Lleida, Luis Vicente
`
`Communication Technologies Group (GTC). Depart.ment of Electronic Engineering & Communications
`Centro Politecnico Superior. C/Maria de Luna 3, 50015-Zaragoza. Spain Universidad de Zaragoza Tel:
`+34-976-761930, FAX: +34-976-762111, E-mail: masgrau@posta.unizar.es
`
`Volume 5 pages 2623 - 2626
`
`ABSTRACT
`
`A new algorithm for speech enhancement based on the iterative Wiener filtering method due to Lim-Oppenheim
`[1] is presented. We propose the use of a generalized non-quadratic cost function in addition to the classical
`MSE term (quadratic term). The proposed cost function includes two signal-error cross- correlation terms and a
`L2 norm term of the filter weights. The signal-error cross- correlation terms reduce both the residual noise and
`the signal distortion in the enhanced speech. The L2 norm term of the filter weights reduces the overall gain of
`the filter, decreasing the weight noise variance and removing the side lobe of the filter response. Two solutions
`to the new cost function are presented: the classical non-causal type (ideal Wiener), working in the frequency
`
`https://web.archive.org/web/19991021233509/http://www.wcl2.ee.upatras.gr:80/eurthaa.html
`
`8/9
`
`Page 8 of 9
`
`

`

`Session ThAA Noise Mitigation, Speech Enhancement II
`5/24/22, 12:40 PM
`domain; and a causal finite length in the time domain. In both cases, as Lim's algorithm, the filter output of each
`iteration is used as "noiseless" speech signal for the following one. Simulation results demonstrate the
`effectiveness of these algorithms.
`
`https://web.archive.org/web/19991021233509/http://www.wcl2.ee.upatras.gr:80/eurthaa.html
`
`9/9
`
`Page 9 of 9
`
`