Douglas O’Shaughnessy

Professeur INRS

Expertises

Traitement de la parole

  • Professeur à l’INRS

Téléphone
514 228-7012

Télécopieur
450 929-8102

Courriel
douglas.oshaughnessy@emt.inrs.ca

Centre Énergie Matériaux Télécommunications

800, De La Gauchetière Ouest
Bureau 6900
Montréal (Québec)  H5A 1K6
CANADA

 

Voir le centre

Intérêts de recherche

Le professeur Douglas O’Shaughnessy a acquis une grande notoriété dans plusieurs domaines de recherche dont : la reconnaissance automatique de la parole par ordinateur, la synthèse automatique de la parole à partir du texte, le codage de la parole et le dialogue verbal entre les humains et les ordinateurs.

Le professeur O’Shaugnessy est impliqué dans nombre de projets spécifiques dont :

  • L’analyse de voix de différents locuteurs
  • L’utilisation de l’information suprasegmentale en reconnaissance de la parole
  • La reconnaissance de la parole par transitions spectrales
  • L’approche de systèmes experts à la reconnaissance de la parole continue

Formation universitaire

  • Maîtrise, génie électrique et informatique, Massachusetts Institute of Technology, Cambridge, États-Unis
  • Doctorat, génie électrique et informatique, Massachusetts Institute of Technology, Cambridge, États-Unis

Projets de recherche en cours

Amélioration de la robustesse de systèmes de reconnaissance de parole automatique par une meilleure adaptation.

Collaborations

  • Scansoft (anciennement Speechworks Inc.)
  • Marcel Gabrea (ETS)
  • Jean Rouat (U. Sherbrooke)
  • Sid-Ahmed Selouani (U. Nouveau-Brunswick)
  • Hesham Tolba (U. Alexandria Egypte)
  • Peter Stubley (Locus Dialogue)
  • Pierre Dumouchel (CRIM)

 

Activités scientifiques

  • Fellow de l’Acoustical Society of America
  • Membre du comité d’évaluation des demandes de subventions en génie électrique du CRSNG 2000-2003
  • Senior Member de l’IEEE
  • Éditeur associé du Journal of the Acoustical Society of America
  • Arbitre pour les revues IEEE Transactions on SAP, Canadian Acoustics, Computer Speech and Languages, Signal Processing Letters, Eurospeech, ICSLP, SMC and Conference ISCAS-2002

Publications

S-A. Selouani and Douglas O’Shaughnessy
ROBUSTNESS OF SPEECH RECOGNITION USING GENETIC ALGORITHMS AND A MEL-CEPSTRAL SUBSPACE APPROACH
ICASSP (International Conference on Acoustics, Speech, and Signal Processing), 201-204, May 2004.

Amr Nour-Eldin and Douglas O’Shaughnessy
AUTOMATIC RECOGNITION OF BLUETOOTH SPEECH IN 802.11 INTERFERENCE AND THE EFFECTIVENESS OF INSERTION-BASED COMPENSATION TECHNIQUES
ICASSP, 1033-1076, May 2004.

Li Deng and D. O’SHAUGHNESSY
SPEECH PROCESSING: A Dynamic and Optimization-Oriented Approach
Marcel Dekker Inc. New York, NY, 2003

O’Shaughnessy D.
Interacting with computers by voice: Automatic speech recognition and synthesis
Proceedings of the IEEE, 2003, Vol: 91(9) Pages:1272-1305

Selouani S.A., O’Shaughnessy D
On the use of evolutionary algorithms to improve the robustness of continuous speech recognition systems in adverse conditions
Eurasip Journal on Applied Signal Processing, 2003, Vol: 2003(8) Pages: 814-823

W. Zhu & D. O’SHAUGHNESSY
Using noise reduction and spectral emphasis techniques to improve ASR performance in noisy conditions
ASRU Symposium, 6 pages, Nov. 2003.

X. Wang & D. O’SHAUGHNESSY
Improving the Efficiency of Automatic Speech Recognition by Feature Transformation and Dimensionality Reduction
Eurospeech, 1025-1028, Sept. 2003

S-A. Selouani, H. Tolba, and D. O’SHAUGHNESSY
Comparative Experiments to Evaluate the Use of Auditory-Based Acoustic Distinctive Features and Formant Cues for Robust Automatic Speech Recognition in Low-SNR Car Environments
Eurospeech, 3085-3088, Sept. 2003.

S-A. Selouani, H. Tolba, and D. O’SHAUGHNESSY
Auditory-based Acoustic Distinctive Features and Spectral Cues for Robust Automatic Speech Recognition in Low-SNR Car Environments
HLT-NAACL 2003, Human Language Technology Conference of the North American Association for Computational Linguistics, CP volume, 91-94, Edmonton, Canada, Spring 2003.

D. O’SHAUGHNESSY & S-A. Selouani
Robust automatic recognition of telephone speech
J. Acoustical Society of America, vol. 113, 2198, April 2003.

D. O’SHAUGHNESSY
Speech Processing in Encyclopedia of Telecommunications, J. Proakis, ed., Wiley Publ., 20 pages, 2002.

D. O’SHAUGHNESSY
Better analysis for automatic speech recognition
Canadian Acoustics, 30, no. 3, 148-149, Sept. 2002.

S-A. Selouani and D. O’SHAUGHNESSY
Noise-Robust Speech Recognition in Car Environments using Genetic Algorithms and a MEL-Cepstral Subspace Approach
International Conf. on Spoken Language Processing (ICSLP), 2173-2176, September 2002.

H. Tolba, and D. O’SHAUGHNESSY
Comparative Experiments to Evaluate the Use of Auditory-Based Acoustic Distinctive Features and Formant Cues Using a Multi-Stream Paradigm for Automatic Speech Recognition
ICSLP, 2113-2116, September 2002.

O. Halmi and D. O’SHAUGHNESSY
On Improving the Performance of Analysis-by-Synthesis Coding Using a Multi-Magnitude Algebraic Code-Book Excitation Signal
ICSLP, 1857-1860, September 2002

S-A. Selouani and D. O’SHAUGHNESSY
A Hybrid HMM/Autoregressive Time-Delay Neural Network Automatic Speech Recognition System
EUSIPCO (European Signal Processing Conf.), paper 108, 4 pages, September 2002.

D. O’SHAUGHNESSY
Improving analysis techniques for automatic speech recognition
45th Midwest Symposium on Circuits and Systems, paper 1014, 4 pages, August 2002.

S-A. Selouani, H.Tolba, and D. O’SHAUGHNESSY
Distinctive Features, Formants and Cepstral Coefficients to Improve Automatic Speech Recognition
IASTED International Conference on Signal Processing, Pattern Recognition, and Applications (SPPRA), paper 370-087, 4 pages, June 2002.

Q. Zeng and D. O’SHAUGHNESSY
Optimum Design of Near-field Sensor Arrays
IEEE AP-S International Symposium and USNC/URSI Radio Science Meeting, June 2002.

H. Tolba and D. O’SHAUGHNESSY
Auditory-based Acoustic Distinctive Features and Spectral Cues for Automatic Speech Recognition Using a Multi-Stream Paradigm
ICASSP (International Conf. on Acoustics, Speech and Signal Processing), 837-840, May 2002.

Q. Zeng and D. O’SHAUGHNESSY
Broadband array design in a broad sense
CCECE (Canadian Conference on Electrical and Computer Engineering), 4 pages, May 2002.

D. O’SHAUGHNESSY & H. Tolba
Speaker Adaptation of HMMs Using Evolutionary Strategy-Based Linear Regression
J. Acoustical Society of America, vol. 111, 2477, June 2002.

S-A. Selouani & D. O’SHAUGHNESSY
Connectionist Mixture of Experts and Auditory-Based Parameters for a Better Identification of Complex Phonetic Features
ISCA Intern. Workshop on Temporal Intergration in the Perception of Speech (TIPS), April 2002.

O’Shaughnessy D.
Better analysis for automatic speech recognition
Canadian Acoustics, 2002, Vol: 30(3) Pages:148-149

H. Tolba & D. O’SHAUGHNESSY
Speech recognition by intelligent machines
IEEE Canadian Review, 38, 20-23, summer 2001.

H.Tolba & D. O’SHAUGHNESSY
Robust Automatic Speech Recognition in Low-SNR Car Environments by the Application of a Connectionist Subspace-Based Approach to the Mel-based Cepstral Coefficients
Eurospeech, 1577-1580, sept. 2001.

H. Ezaidi, J. Rouat & D. O’SHAUGHNESSY
Combining pitch and MFCC for speaker recognition systems
Eurospeech, 2825-2828, sept. 2001.

H.Tolba & D. O’SHAUGHNESSY
Problems and Solutions for Robust Speech Recognition of the Spontaneous French-Speech in Wireless Environments
International Conf. on Speech Processing (ICSP), 5-8, aout 2001.

H.Tolba, Sid-Ahmed Selouani & D. O’SHAUGHNESSY
Comparative Experiments to Evaluate a Connectionist Subspace-Based Pre-Processing Approach to Robust Automatic Speech Recognition in Low-SNR Car Environments
International Conf. on Speech Processing (ICSP), 1-4, aout 2001.

D. O’SHAUGHNESSY & H. Tolba
Efficient automatic recognition of spoken digits
Journal of the Acoustical Society of America, vol. 109, 2316, June 2001.