ISCA Archive RSR 1997 Search
  ISCA Archive Search

Click on column names to sort.

Searching uses the 'and' of terms e.g. Smith Interspeech matches all papers by Smith in any Interspeech. The order of terms is not significant.

Use double quotes for exact phrasal matches e.g. "acoustic features".

Case is ignored.

Diacritics are optional e.g. lefevre also matches lefèvre (but not vice versa).

It can be useful to turn off spell-checking for the search box in your browser preferences.

If you prefer to scroll rather than page, increase the number in the show entries dropdown.


Robust Speech Recognition for Unknown Communication Channels

Pont-à-Mousson, France
17-18 April 1997

Table of Contents and Access to Abstracts

Should recognizers have ears?
Hynek Hermansky

Recent advances in robust speech recognition
Sadaoki Furui

Discussion on the introductory session
Herman Steeneken, Luc Gagnon, Jerry O'Leary

On the origins of speech intelligibility in the real world
Steven Greenberg

Compensation for environmental degradation in automatic speech recognition
Richard M. Stern, Bhiksha Raj, Pedro J. Moreno

Robust features and environmental compensation: a few comments
Nelson Morgan

On feature and model compensation approach to robust speech recognition
Chin-Hui Lee

NICE model-based compensation schemes for robust speech recognition
M. J. F. Gales

Speculations on knowledge versus data in ASR
Hynek Hermansky

On the future trends of hands-free ASR: variabilities in the environmental conditions and in the acoustic transduction
Maurizio Omologo

Issues relating to the future of ASR for telecommunications applications
Shigeki Sagayama, Kiyoaki Aikawa

Noise suppression and acoustic model controlled loudness mean normalization in an auditory model-based acoustic front-end
Jan Verhasselt, Halewijn Vereecken, Jean-Pierre Martens

Improving ASR performance for reverberant speech
Brian E. D. Kingsbury, Nelson Morgan, Steven Greenberg

Intelligibility improvements obtained by an enhancement method applied to speech corrupted by noise and reverberation
Paul W. Shields, Douglas R. Campbell

Robust speech recognition based on multi-stream features
Stephane Dupont, Hervé Bourlard, Christophe Ris

Application of VTS to environment compensation with noise statistics
Nam Soo Kim, Do Yeong Kim, Byung Goo Kong, Sang Ryong Kim

Recent advances in addressing sources of non-linguistic information
Hynek Hermansky, Carlos Avendano, Sarel van Vuuren, Sangita Tibrewala

Noise robust HMM-based speech recognition using segmental cepstral feature vector normalization
Olli Viikki, Kari Laurila

Wavelet based noise reduction for speech recognition
Erica Bernstein, Ward Evans

A unified parameterization scheme for noisy speech recognition
Javier Hernando, Climent Nadeu

Channel normalisation using phase-corrected RASTA
Johan de Veth, Louis Boves

A multi-microphone sub-band adaptive speech enhancement system employing diverse sub-band processing
Amir Hussain, Douglas R. Campbell, Thomas J. Moir

Comparison of algorithms for microphone equalization in continuous speech recognition
C. Vair, N. Chiminelli, L. Fissore, G. Micca

Cepstral compensation using statistical linearization
Bhiksha Raj, Evandro Gouvea, Richard M. Stern

Robust vector quantization for noisy channels using a self-organizing pseudo-map
Abdelkader Amraoui, Pierre Dufour

Improving robustness in HMM based speech recognition through simultaneous frequency warping and spectral shaping
Richard C. Rose, Alexandros Potamianos

Robust multi-channel signal separation
Gül Aydin, Yasemin Yardimci, A. Enis Cetin

Neural networks contribution to robust HMM systems
Jean-Baptiste Puel

Robust error correction of continuous speech recognition
Eric K. Ringger, James R. Allen

Adaptation of model parameters by HMM decomposition in noisy reverberant environments
Tetsuya Takiguchi, Satoshi Nakamura, Qiang Huo, Kiyohiro Shikano

Noise reduction with spectral subtraction and median filtering for suppression of musical tones
Klaus Linhard, Heinz Klemm

Commercial speech recognisers performance under adverse conditions, a survey
H. Agaiby, C. Fyfe, S. McGlinchey, T. J. Moir

Automatic segmentation and labeling of speech recorded in unknown noisy channel environments
Bryan L. Pellom, John H. L. Hansen

A user friendly remote speech input unit in spontaneous speech translation system
Youngjoo Suh, Jun Park, Youngjik Lee

Automatic speech recognition for time-varying channels
Keith M. Pouting

ASR in highly non-stationary environments using adaptive noise cancelling techniques
R. Martinez, A. Alvarez, V. Nieto, V. Rodellar, P. Gomez

Audio-visual talker localization for hand-free speech recognition
Harouna Kabre

Evaluation of digit recognition over the telephone network
Daniele Falavigna, Roberto Gretter

Hands-free speech recognition in a noisy and reverberant environment
Maurizio Omologo, Marco Matassoni, Piergiorgio Svaizer, Diego Giuliani

A multi-microphone sub-band adaptive speech enhancement system employing artificial neural network based non-linear filters
Amir Hussain, Douglas R. Campbell

Incorporation of noise pre-processing into an entrenched speech recognition system
Vijay Raman, Vidhya Ramanujam

Model compensation for additive and convolutive noises in training and test data
Driss Matrouf, Jean-Luc Gauvain

MUSE: MUltipath stochastic equalization - a theoretical framework to combine equalization and stochastic modeling
C. Mokbel

Robust HMM architectures for cellular phone speech recognition
Jean-Baptiste Puel, Bruno Jacob

Search papers

Table of Contents and Access to Abstracts