RESPITE: Publications

RESPITE Project Publications

Articles in International Journals

2002

Martin Heckmann, Frédéric Berthommier, and Kristian Kroschel, Noise adaptive stream weighting in audio-visual speech recognition, accepted for JASP, 2002, PDF

2001

S. Choi, H. Hong, H. Glotin and F. Berthommier, Multichannel signal separation for cocktail party speech recognition: a dynamic recurrent network, submitted to Neurocomputing, 2001, PostScript
M. P. Cooke, P.D. Green, L. Josifovski and A. Vizinho, Robust automatic speech recognition with missing and unreliable acoustic data, Speech Communication, 2001 PDF
Andrew Morris, Astrid Hagen, Hervé Glotin, and Hervé Bourlard, Multi-stream adaptive evidence combination for noise robust ASR Speech Communication, 2001, vol 34, pp 25-40 PostScript

2000

C. Ris and S. Dupont, Assessing local noise level estimation methods: application to noise robust ASR, submitted to Speech Communication, 2000 PostScript

Articles in Conference Proceedings

2002

K.Palomaki, G.Brown and J.Barker, Missing data speech recognition in reverberant conditions, Accepted for ICASSP 2002, Denmark, September 2001. PDF

2001

J. Barker, P.Green and M.P. Cooke, Linking Auditory Scene Analysis and Robust ASR by Missing Data Techniques, WISP 2001, Stratford-upon-Avon, UK, PostScript|PDF
J. Barker, M.Cooke and P.Green, Robust ASR Based on Clean Speech Models: An Evaluation of Missing Data Techniques for Connected Digit Recognition in Noise, Accepted for Eurospeech 2001, Special Event on Noise Robust Recognition, Denmark, September 2001. PostScript|PDF
G. J. Brown, D. L. Wang & J. Barker A neural oscillator sound separator for missing data speech recognition, Proceedings of IJCNN, Washington DC, July 14-19. PDF
F. Berthommier Audio-visual recognition of spectrally reduced speech, Proceedings of AVSP' 01, Aalborg, Denmark, September 2001. PDF|Presentation
F. Berthommier and S.Choi Evaluation of CASA and BSS models for cocktail-party speech segregation, Accepted for ICA'01, San Diega, USA, 2001. PDF
F. Berthommier and S.Choi Evaluation of CASA and BSS models for subband cocktail-party speech segregation, Proceedings of ICSP' 01, Daejeon, Korea, 2001. Postscript|PDF
S. Dupont and C. Ris, Multi-band with contaminated training data, Eurospeech-2001, Aalborg, Denmark, PDF
D.P.W. Ellis and M.J. Reyes Gomez, Investigations into Tandem Acoustic Modeling for the Aurora Task, Eurospeech 2001, Special Event on Noise Robust Recognition, Denmark, September 2001. PDF
P.Green, J. Barker, M.P. Cooke and L. Josifovski, Handling Missing and Unreliable Information in Speech Recognition, AISTATS 2001, Florida, PostScript|Slides
Hagen, H. & Bourlard, H., Error Correcting Posterior Combination for Robust Multi-Band Speech Recognition, Proc. Eurospeech 2001.PostScript|PDF
Hagen, H., Bourlard, H. & Morris, A.C., Adaptive ML-weighting in multi-band recombination of Gaussian mixture ASR, Proc. ICASSP'2001.PostScript|PDF
M. Heckmann, F. Berthommier, and K. Kroschel, Optimal Weighting of Posteriors For Audio-Visual Speech Recognition, Accepted for ICCASP-2001, Salt Lake City, Utah, PostScript|PDF
M. Heckmann, F. Berthommier, and K. Kroschel, Noise adaptive stream weighting in audio-visual speech recognition, Submitted for JASP, PDF
M. Heckmann, T. Wild, F. Berthommier, and K. Kroschel, Comparing Audio- and A-Posteriori-Probability-Based Stream Confidence Measures for Audio-Visual Speech Recognition, Accepted for Eurospeech-2001, Aalborg, Denmark, PostScript|PDF
M. Heckmann, F. Berthommier, and K. Kroschel, A Hybrid ANN/HMM Audio-Visual Speech Recognition System, Submitted for AVSP-2001, Aalborg, Denmark, PostScript|PDF
J. M. Hilario, J.M. Ferrer and F. Class Evaluation of robust feature extraction and acoustic modelling algorithms/systems by interfacing ASR systems, Accepted for CRAC'01, Aalborg, Denmark, 2001. PDF
A. C. Morris, J. Barker and H. Bourlard, From Missing Data to Maybe Useful Data: Soft Data Modelling for Noise Robust ASR, WISP 2001, Stratford-upon-Avon, UK, PostScript|PDF
Morris, A.C., Hagen, H. & Bourlard, H. MAP Combination of Multi-Stream HMM or HMM/ANN Experts, Accepted for Eurospeech 2001, Special Event on Noise Robust Recognition, Denmark, September 2001. PostScript|PDF

2000

J. Barker, M.P. Cooke and D.P.W.Ellis, Decoding speech in the presence of other sound sources, Proc. ICSLP-2000, Beijing PostScript|Abstract
J. Barker, L. Josifovski, M.P. Cooke and P.D. Green , Soft decisions in missing data techniques for robust automatic speech recognition, Proc. ICSLP-2000, Beijing, PostScript|Abstract
Frédéric Berthommier and Hervé Glotin,, Reconnaissance de la parole dans le bruit après renforcement fondé sur l'harmonicité, to appear in "Journée d'Études sur la Parole, Aussois, 2000" PostScript
F. Berthommier, H. Glotin and E. Tessier, A front-end using the harmonicity cue for speech enhancement in loud noise, Proc. ICSLP-2000, Beijing, PostScript
S. Choi, H. Hong, H. Glotin and F. Berthommier, Multichannel signal separation for cocktail party speech recognition: a dynamic recurrent network, Proc. ICSLP-2000, Beijing, PostScript
Ellis, D.P.W. and Bilmes, J.A., Using mutual information to design feature combinations, Proc. ICSLP-2000, Beijing, PDF
Ellis, D.P.W., Stream combination before and/or after the acoustic model, Submitted to ICASSP 2000, Istanbul PDF
Ellis, D., Hermansky, H. and Sharma, S., Tandem connectionist feature stream extraction for conventional HMM systems , ICASSP-2000, Istanbul PDF
H. Glotin and F. Berthommier, Test of several external posterior weighting functions for multiband Full Combination ASR, Proc. ICSLP-2000, Beijing, PostScript
A. Grosgeorges, F. Berthommier, F. Apoux and C. Lorenzi, Détection de la modulation d'amplitude liée au voisement: comparaison entre expérimentation et modélisation, to appear in "Journée d'Études sur la Parole, Aussois, 2000" PostScript
A. Grosgeorges, F. Berthommier and C. Lorenzi, Effect of masking spectrally reduced speech with modulated noise , to be presented at the 140th meeting of the ASA and Noise-Con, Newport Beach, CA, USA, 2000 PostScript (abstract)
A. Hagen and H. Glotin,, Études comparatives des robustesses au bruit de l'approche `Full Combination' et de son approximation , to appear in "Journée d'Études sur la Parole, Aussois, 2000" PostScript
A. Hagen, A. Morris, and H. Bourlard, From Multi-Band Full Combination to Multi-Stream Full Combination Processing in Robust ASR, Proc. ISCA ITRW ASR2000 PostScript
A. Hagen and H. Bourlard, Using Multiple Time Scales in the Framework of Multi-Stream Speech Recognition, Proc. ICSLP-2000, Beijing, PostScript
A. Hagen and A. Morris, Comparison of HMM experts with MLP experts in the Full Combination Multi-Band Approach to Robust ASR Proc. ICSLP-2000, Beijing, PostScript
M. Heckmann, F. Berthommier, C. Savariaux and K. Kroschel, Labeling audio-visual speech corpora and training and training an ANN/HMM speech recognition system, Accepted for ICSLP-2000, Beijing, PostScript
Heckmann, M., Berthommier, F., Charbonneau, V. and Kroschel, K., A multi-stage methodology to setup an ANN/HMM audio-visual speech recognition system, IAR2000, Nancy, PostScript
Andrew Morris, Some applications of a priori knowledge in multi-stream HMM and HMM/ANN based ASR, "Proc. Workshop on Phonetics and Phonology in ASR, 2000" PostScript
Andrew Morris, Ljubomir Josifovski, Hervé Bourlard, Martin Cooke, Phil Green, A neural network for classification with incomplete data: application to robust ASR, Proc. ICSLP-2000, Beijing, PostScript
S. Skorik and F. Berthommier, On a cepstrum-based speech detector robust to white noise, Accepted for Specom2000, St. Petersbourg, PDF|PostScript
Todd A. Stephenson, Hervé Bourlard, Samy Bengio, and Andrew C. Morris, Automatic Speech Recognition using Dynamic Bayesian Networks with both Acoustic and Articulatory Variables, Proc. ICSLP-2000, Beijing, PostScript

1999

Frédéric Berthommier, Hervé Glotin, Emmanuel Tessier, and Hervé Bourlard, Interfacing of CASA and partial recognition based on a multistream technique., ICSLP 98, Sidney, Australia 1998 PostScript|BibTeX
Frédéric Berthommier and Hervé Glotin, A new SNR-feature mapping for robust multistream speech recognition, ICPhS, San Francisco, 1999 PostScript|PDF|BibTeX
Frédéric Berthommier and Hervé Glotin, A measure of speech and pitch reliability from voicing, CASA'99 workshop, Stockholm, 1999 PostScript|BibTeX
Hervé Bourlard, Non-stationary multi-channel (multi-stream) processing towards robust and adaptive ASR,in "Robust Methods for Speech Recognition in Adverse Conditions", Tampere, 1999 PostScript|BibTeX
Seunjin Choi, Youngki Lyu, Frédéric Berthommier, Hervé Glotin and Andrzej Cichocki, Blind separation of delayed and superimposed acoustic sources: learning algorithms an experimental study, ICSP'99, Seoul, 1999 PostScript|BibTeX
M. Cooke, P. Green, L. Josifovski and A. Vizinho, Robust ASR with unreliable data and minimal assumptions, in "Robust Methods for Speech Recognition in Adverse Conditions", Tampere, 1999 Postscript
Stephane Dupont and Chrsitophe Ris, Assessing local noise level estimation methods, in "Robust Methods for Speech Recognition in Adverse Conditions", Tampere, 1999 Postscript
Glotin Hervé, Frédéric Berthommier, Emmanuel Tessier, and Hervé Bourlardr, Interfacing of CASA and multistream recognition. TSD'98-Text, Speech and Dialog International Workshop, pages 207-212, Brno, Czech Republic, Sept 1998. (Ordering at http://www.fi.muni.cz/tsd98/ ) PostScript|BibTeX
Hervé Glotin, Frédéric Berthommier and Emmanuel Tessier, A CASA-Labelling model using the localisation cue for, robust cocktail-party speech recognition, Eurospeech'99, Budapest, 1999 PostScript|PDF|BibTeX
A. Hagen, A. Morris, and H. Bourlard, Different Weighting Schemes in the Full Combination Subbands Approach for Noise Robust ASR,in "Robust Methods for Speech Recognition in Adverse Conditions", Tampere, 1999 PostScript|Abstract|BibTeX
L. Josifovski, M. Cooke, P. Green and A. Vizinho, State based imputation of missing data for robust speech recognition and speech enhancement , Eurospeech'99, Budapest, 1999 PostScript
Kermorvant, C. and Morris, A., A comparison of two strategies for ASR in additive noise : Missing Data and Spectral Subtraction, Eurospeech'99, Budapest, 1999 PostScript|BibTeX
Andrew Morris, Astrid Hagen and Hervé Bourlard, The full combination sub-bands approach to noise robust HMM/ANN based ASR, Eurospeech'99, Budapest, 1999 PostScript|BibTeX
Emmanuel Tessier, Frédéric Berthommier, Hervé Glotin and Seunjin Choi, A CASA front-end using the localisation cue for segregation and then cocktail-party speech recognition, ICSP'99, Seoul, 1999 PostScript|PDF|BibTeX
A. Vizinho, P. Green, M. Cooke and L. Josifovski, Missing data theory, spectral subtraction and signal-to-noise estimation for robust ASR: An integrated study, Eurospeech'99, Budapest, 1999 PostScript

Technical Reports

2000

Andrew Morris, A neural network for classification with incomplete data , IDIAP Research Report, 00-23, 2000 PostScript

1999

Andrew Morris, Latent variable decomposition for posteriors or likelihood based subband ASR, IDIAP Communication, 99-04, 1999 PostScript

These pages are maintained by Jon Barker, jon@dcs.shef.ac.uk

Last modified: Tue Feb 5 12:48:33 GMT 2002