Refereed conference papers

  1. Luyet, G., Gighe, P., Asaei, A., and Bourlard, H. (2016), “Low-Rank Representation of Nearest Neighbor Posterior Probabilities to Enhance DNN Based Acoustic Modeling,” Proc. of Interspeech’2016, San Francisco, 8-15 September 2016.
  2. Ram, D., Asaei, A. and Bourlard, H. (2016), “Subspace Detection of DNN Posterior Probabilities via Sprase Representation for Query by Example Spoken Term Detection,” Proc. of Interspeech’2016, San Francisco, 8-15 September 2016.
  3. Ferras, M., Madikeri, S., Dey, S., Motlicek, P., and Bourlard, H. (2016), “Inter-Task System Fusion for Speaker Recognition,”Proc. of Interspeech’2016, San Francisco, 8-15 September 2016.
  4. Asaei, A., Luyet, G., Cernak, M., and Bourlard, H. (2016), “Phonetic and Phonological Posterior Search Space Hashing Exploiting Class-Specific Sparsity Structures,” Proc. of Interspeech’2016, San Francisco, 8-15 September 2016.
  5. Cernak, M., Asaei, A., Honnet, P.-E., Garner, P., and Bourlard, H. (2016), “Sound Pattern Matching for Automatic Prosodic Event Detection,” Proc. of Interspeech’2016, San Francisco, 8-15 September 2016.
  6. Dighe, P., Luyet, G., Asaei, A., and Bourlard, H. (2016), “Exploiting Low-Dimensional Structures to Enhance DNN Based Acoustic Modeling in Speech Recognition,” Proc. of the Intl. Conference on Acoustics, Speech and Signal Processing (ICASSP’2016), Shanghai, China, 20-25 March 2016.
  7. Ferras, M., Madikeri, S., Motlicek, P. and Bourlard, H. (2016), “System Fusion and Speaker Linking for Longitudinal Diarization of TV Shows,” Proc. of the Intl. Conference on Acoustics, Speech and Signal Processing (ICASSP’2016), Shanghai, China, 20-25 March 2016.
  8. Asaei, A., Cernak M., and Bourlard, H. (2015), “On compressibility of Neural Network Phonological Features for Low Bit Rate Speech Coding”, Interspeech 2015, Dresden, Germany, 6-10 Sep. 2015.
  9. Ullmann, R., Rasipuram, R., Magimai-Doss, M., and Bourlard, H (2015), “Objective intelligibility assessment of text-to-speech systems through utterance verification”, Best PhD Student paper award, Interspeech 2015, Dresden, Germany, 6-10 Sep. 2015.
  10. Ram, D., Asaei, A., Dighe, P., and Bourlard, H. (2015), “Sparse modeling of posterior exemplars for keyword detection”, Interspeech 2015, Dresden, Germany, 6-10 Sep. 2015.
  11. Dighe, P., Asaei, A., and Bourlard, H. (2015), “Dictionary Learning for Sparse Representation of Neural Network Exemplars in Speech Recognition,” submitted to Signal Processing with Adaptive Sparse Sructured Representations (SPARS’2015), July -9, Cambridge, UK.
  12. Dighe, P., Asaei, A., and Bourlard, H. (2015), “Sparse Modeling of Neural Network Posterior Probabilities for Exemplar-Based Speech Recognition,” submitted to Signal Processing with Adaptive Sparse Sructured Representations (SPARS’2015), July -9, Cambridge, UK.
  13. Asaei, A., Mohammadiha, N., Taghizageh, M., Doclo, S., and Bourlard, H. (2015), “On Application of Non-Negative Matrix factorization for Ad-Hoc Microphone Array Calibration from Incomplete Noisy Distance,” Proc. of IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP’2015), Brisbane, 19-24 April 2015.
  14. Velasco, J., Taghizadeh, M., Asaei, A., Bourlard, H., Martin-Arguedas, C.J., Macias-Guarasa, J., and Pizarro, D. (2015), “Novel GCC-PHAT Model in Diffuse Sound Field for Microphone Array Pairwise Distance Based Calibration,” Proc. of IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP’2015), Brisbane, 19-24 April 2015.
  15. Ullmann, R., Magimai-Doss, M., and Bourlard, H. (2015), “Objective Speech Intelligibility Assessment Through Comparison of Phoneme Class Conditional Probability Sequences,” Proc. of IEEE Intl, Conf. on Acoustics, Speech and Signal Processing (ICASSP’2015), Brisbane, 19-24 April 2015.
  16. Madikeri, S. and Bourlard, H. (2015), “KL-HMM Based Speaker Diarization System for Meetings,” Proc. of IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP’2015), Brisbane, 19-24 April 2015.
  17. Madikeri, S., Motlicek, P., and Bourlard, H. (2015) “Combining SGMM Speaker Vectors and KL-HMM Approach for Speaker Diarization,” Proc. of IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP’2015), Brisbane, 19-24 April 2015.
  18. Taghizadeh, M., Haghighatshoar, S., Asaei, A., Garner, P.N, and Bourlard, H. (2015), “Robust Microphone Placement for Source Localization from Noisy Distance Measurements,” Proc. of IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP’2015), Brisbane, 19-24 April 2015.
  19. Bahaadini, S., Asaei, A., Imseng, D., and Bourlard, H. (2014), “Posterior-based Sparse Representation for Automatic Speech Recognition,” Proceedings of Interspeech 2014, Singapore, 14-18 September 2014.
  20. Dighe, P., Ferràs, M., and Bourlard, H. (2014), “Detecting and Labeling Speakers on Overlapping Speech using Vector taylor Series,” Proceedings of Interspeech 2014, Singapore, 14-18 September 2014.
  21. Ferràs, M and Bourlard, H. (2014), “Multi-Source Posteriors for Speech Activity Detection on Public Talks,” Proceedings of Interspeech 2014, Singapore, 14-18 September 2014.
  22. Ferràs, M, Masneri, S., Schreer, O., and Bourlard, H., “Diarizing Large Corpora using Multimodal Speaker Linking,” Proceedings of Interspeech 2014, Singapore, 14-18 September 2014.
  23. Sree Harsha Yella, Petr Motlicek and Hervé Bourlard, “Phoneme Background Model for Information Bottleneck based Speaker Diarization,” Proceedings of Interspeech 2014, Singapore, 14-18 September 2014.
  24. Ashtosh Sapru and Hervé Bourlard, “Detecting speaker roles and topic changes in multiparty conversations using latent topic models,” Proceedings of Interspeech 2014, Singapore, 14-18 September 2014.
  25. Dighe, P., Ferràs, M., and Bourlard. H. (2014), “Modeling Overlapping Speech Using Vector Taylor Series,” Proceedings of Odyssey 2014 - The Speaker and Language Recognition Workshop, Joensuu, Finland, 16-19 June 2014.
  26. Taghizadeh, M.J., Asaei, A., Garner, P.N, and Bourlard, H. (2014), “Ad-hoc microphone array calibration from partial distance measurements,” 4th Joint Workshop on Hands-Free Speech Communication and Microphone Arrays (HSCMA), Nancy, France, May 12-14, 2014. Nominated for Best Student Paper Award.
  27. Asaei, A., Bourlard, H., Taghizadeh, M.J., and V. Cevher, M. (2014), “Model-based Sparse Component Analysis for Reverberant Speech Localization”, Proceedings of the IEEE Intl. Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, May 4-9, 2014.
  28. Madikeri, S. and Bourlard, H. (2014), “Filterbank Slope based Features for Speaker Diarization”, Proceedings of the IEEE Intl. Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, May 4-9, 2014.
  29. Sapru, A., Yella, S.H., and Bourlard, H. (2014), “Improving Speaker Diarization using social role information”, Proceedings of the IEEE Intl. Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, May 4-9, 2014.
  30. Imseng, D., Potard, B., Motlicek, P., Nanchen, A., and Bourlard, H. (2014), “Exploiting un-transcribed foreign data for speech recognition in well-resourced languages”, Proceedings of the IEEE Intl. Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, May 4-9, 2014.
  31. Vu, N.T., Imseng, D., Povey, D., Motlicek, P., Schultz, T., and Bourlard, H. (2014), “Multilingual Deep Neural Network Based Acoustic Modeling For Rapid Language Adaptation”, Proceedings of the IEEE Intl. Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, May 4-9, 2014.
  32. Yella, S.H. and Bourlard, H. (2014), “Information Bottleneck based Speaker Diarization of Meetings using Non-speech as Side Information”, Proceedings of the IEEE Intl. Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, May 4-9, 2014.
  33. Sapru, A. and Bourlard, H. (2013), “Investigating the Impact of Language Style and Vocal Expression on Social Roles of Participants in Professional Meetings,” Intl. Conf. on Affective Computing and Intelligent Interaction (ACII 2013), Geneva, Switzerland, Sep.2-5, 2013.
  34. Bourlard, H., Ferras, M., Pappas, N., Popescu-Belis, A., Renals, S., McInnes, F., Bell, P., Ingram, S., and Guillemot, M. (2013), “Processing and Linking Audio Events in Large Multimedia Archives: The EU inEvent Project,” First Workshop on Speech, Language and Audio in Multimedia, August 22-23, 2013.
  35. Sapru, A. and Bourlard, H. (2013), “Social Role Recognition in Professional Meetings Using Conditional Random Fields,” Proceedings of Interspeech, Lyon, 25-29 August 2013.
  36. Ullmann, R., Bourlard, H., Berger, J., Llagostera Casanovas, A. (2013), ``Noise Intrusiveness Factors in Speech Telecommunications,’’ in Proc. of AIA-DAGA 2013 Conference on Acoustics, Merano, 18-21 March 2013.
  37. Taghizadeh, M.J., Parhizkar, R., Garner, P.N., Bourlard, H. (2013), `` Euclidean Distance Matrix Completion for Ad-hoc Microphone Array Calibration,’’ 18th Intl. Conf. on Digital Signal Processing (DSP’2013), July 1-3, Greece, 2013.
  38. Asaei, A., Raj, B., Bourlard, H., and Cevher, V. (2013), ``A Multipath Sparse Beamforming Method,’’ in Proc. of Signal Processing with Adaptive Sparse Structured Representations (SPARS’2013), July 8-11, 2013, Lausanne, Switzerland.
  39. Ferras, M. and Bourlard, H. (2013), “MLP-Based Factor Analysis for Tandem Speech Recognition,” Proceedings of the IEEE Intl. Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, May 26-31, 2013.
  40. Imseng, D. and Bourlard, H. (2013), “Adaptive Kullback-Leibler Divergence Based Hidden Markov Models,” Proceedings of the IEEE Intl. Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, May 26-31, 2013.
  41. Yella, S. and Bourlard, H. (2013), “Improved Overlap Speech Diarization of Meeting Recordings using Long-Term Conversational Features,” Proceedings of the IEEE Intl. Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, May 26-31, 2013.
  42. Ferras, M. and Bourlard, H. (2012), “Speaker Diarization and Linking on Large Corpora,” Proceedings of the IEEE Workshop on Spoken Language Technology (SLT), Miami, FL, December 2-5, 2012.
  43. Imseng, D., Bourlard, H., Caeser, H., Garner, P.N., Lecorvé, G., and Nanchen, A. (2012), “MediaParl: Bilingual Mixed Language Accented Speech Database,” Proceedings of the IEEE Workshop on Spoken Language Technology (SLT), Miami, FL, December 2-5, 2012.
  44. Soldo, S., Magimai-Doss, M., and Bourlard, H. (2012), “Template-based ASR using Posterior Features and Synthetic References: Comparing Different TTS Systems,” Workshop on Statistical and Perceptual Audition (SAPA), 7-8 September 2012, Portland, OR, USA.
  45. Asaei, A., Ray, B, Bourlard, H., and Cevher, V. (2012), “Structured Sparse Coding for Microphone Array Location Calibration”, Workshop on Statistical and Perceptual Audition (SAPA), 7-8 September 2012, Portland, OR, USA.
  46. Soldo, S., Magimai-Doss, M., and Bourlard, H. (2012), “Synthetic References for Template-based ASR Using Posterior features,” Proceedings of the 13th Annual Conference of the International Speech Communication Association (InterSpeech), Portland, Oregon, September 9-13, 2012.
  47. Li, W. and Bourlard, H. (2012), “Sub-Band Based Log-Energy and its Dynamic Range Stretching for Robust In-Car Speech Recognition,” Proceedings of the 13th Annual Conference of the International Speech Communication Association (InterSpeech), Portland, Oregon, September 9-13, 2012.
  48. Cernak, M., Imseng, D., and Bourlard, H. (2012), “Robust Triphone Mapping for Acoustic Modeling,” Proceedings of the 13th Annual Conference of the International Speech Communication Association (InterSpeech), Portland, Oregon, September 9-13, 2012.
  49. Imseng, D., Dines, J., Motlicek, P., garner, P.N., and Bourlard, H. (2012), “Comparing Different Acoustic Modeling Techniques for Multilingual Boosting,” Proceedings of the 13th Annual Conference of the International Speech Communication Association (InterSpeech), Portland, Oregon, September 9-13, 2012.
  50. Taghizadeh, M., Garner, P., and Bourlard, H. (2012), “Broadband Beampattern for Multi-Channel Speech Acquisition and Distant Speech Recognition,” Proceedings of the IEEE Sensor Array and Multichannel Signal Processing Workshop, Stevens Institute of Technology, Hoboken, NJ, June 17-20, 2012.
  51. Imseng, D, Bourlard, H., and Garner, P. (2012), “Boosting Under-Resourced Speech Recognizers by Exploiting out of Language Data - Case study on Afrikaans,” International Workshop on Spoken Languages Technologies for Under-resourced Languages (SLTU'12), Cape Town, Africa, 7-9 May 2012.
  52. Asaei, A., Davies, M.E., Bourlard, H., and Cevher, V. (2012), “Computational Methods for Structured Sparse Component Analysis for Convolutive Speech Mixtures,” Proceedings of the IEEE Intl. Conference on Acoustic Speech and Signal Processing (ICASSP’2012), 25-30 March 2012, Kyoto, Japan.
  53. Imseng, D., Bourlard, H., and Garner, P.N. (2012), “Using KL-Divergence and Multilingual Information to Improve ASR for Under-Resourced Languages,” Proceedings of the IEEE Intl. Conference on Acoustic Speech and Signal Processing (ICASSP’2012), 25-30 March 2012, Kyoto, Japan.
  54. Asaei, A., Bourlard, H., and Cevher, V. (2011), “Structured Sparse Component Analysis for Convolutive Speech Separation”, submitted to IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA’2011), Mohonk Mountain House, New Paltz, NY, October 16-19, 2011.
  55. Reza Abutalebi, H., Heli, H., Korchagin, D., and Bourlard, H. (2011), “A BSS-Based Approach for Localization of Simultaneous Speakers in Reverberant Conditions”, Proceedings of 19th European Signal Processing Conference (EUSIPCO2011), Barcelona, August 29-September 2, 2006.
  56. Parthasarathi, H., Bourlard, H, Gatica-Perez, D. (2011), “LP Residual Features for Robust, Privacy-Sensitive Speaker Diarization,” Proceedings of Interspeech 2011, Florence, 28-31 August 2011.
  57. Imseng, D., Bourlard H., Dines, J., Garner, P.N., and Magimai.-Doss, M. (2011), “Improving Non-Native ASR Through Stochastic Multilingual Phoneme Space Transformations,” Proceedings of Interspeech 2011, Florence, 28-31 August 2011.
  58. Magimai-Doss, M., Ramya Rasipuram, R., Aradilla, G., and Bourlard, H. (2011), “Grapheme-based Automatic Speech Recognition using KL-HMM,” Proceedings of Interspeech 2011, Florence, 28-31 August 2011.
  59. Asaei, A., Taghizadeh, M. J., Bourlard, H., and Cevher, V. (2011), “Multi-party Speech Recovery Exploiting Structured Sparsity Models,” Proceedings of Interspeech 2011, Florence, 28-31 August 2011.
  60. Pinto, J., Magimai.-Doss, M., Bourlard, H. (2011), “Hierarchical Tandem Features for ASR in Mandarin,” Proceedings of Interspeech 2011, Florence, 28-31 August 2011.
  61. Korchagin, D., Motlicek, P., Duffner, S., and Bourlard, H., (2011), “Just-in-time Multimodal Association and Fusion from Home Entertainment,” IEEE Intl. Conf. on Multimedia and Expo (ICME’2011), Barcelona, July 11-15, 2011.
  62. Taghizadeh, M.J., Garner, P.N., Bourlard, H., and Abutalebi, H.R. (2011), “An Integrated Framework for Multi-Channel Multi-Source Localization and Voice Activity Detection,” to be published in the Proceedings of 3rd Joint Workshop on Hands-free Speech Communication and Microphone Arrays, Edinburgh, 30 May-1 June 2011.
  63. Soldo, S., Magimai-Doss, M., Pinto, J., and Bourlard, H. (2011), “Posterior Features for Template-based ASR,” Proc. of the IEEE Intl. Conference on Acoustics, Speech, and Signal Processing, Prague, Czech Republic, 2011.
  64. Features for Template-based ASR”, Proceedings of the IEEE Intl. Conference on Acoustic Speech and Signal Processing (ICASSP’2011), 22-27 May 2011, Prague.
  65. Asaei, A., Bourlard, H., and Cevher, C. (2011), “Model-Based Compressive Sensing For Multi-Party Distant Speech Recognition”, Proceedings of the IEEE Intl. Conference on Acoustic Speech and Signal Processing (ICASSP’2011), 22-27 May 2011, Prague. Best PhD Student Paper Award.
  66. Imseng, D., Bourlard, H., Magimai-Doss, M., and Dines, J. (2011), “Language Dependent Universal Phoneme Posterior Estimation for Mixed Language Speech Recognition,” Proceedings of the IEEE Intl. Conference on Acoustic Speech and Signal Processing (ICASSP’2011), 22-27 May 2011, Prague.
  67. Garau, G., Dielmann, A., and Bourlard, H. (2010), “Audio-Visual Synchronization for Speaker Diarization,” in Proceedings of Interspeech 2010, Makuhari, Japan, 26-30 September 2010.
  68. Dielmann, A., Garau, G., and Bourlard, H. (2010), “Floor Holder Detection and End for Speaker Turn Prediction in Meetings,” in Proceedings of Interspeech 2010, Makuhari, Japan, 26-30 September 2010.
  69. Asaei, A., Bourlard, H., and Garner, P. (2010), “Sparse Component Analysis for Speech Recognition in Multi-Speaker Environment,” in Proceedings of Interspeech 2010, Makuhari, Japan, 26-30 September 2010.
  70. Vijayasenan, D., Valente, F., and Bourlard, H. (2010), “Advances in Fast Multistream Diarization based on the Information Bottleneck Framework,” in Proceedings of Interspeech 2010, Makuhari, Japan, 26-30 September 2010.
  71. Imseng, D, Magimai-Doss, M., and Bourlard, H. (2010), “Hierarchical Multilayer Perceptron based Language Identification,” in Proceedings of Interspeech 2010, Makuhari, Japan, 26-30 September 2010.
  72. Imseng, D., Bourlard, H., and Magimai-Doss, M., “Towards Mixed Language Speech Recognition Systems,” in Proceedings of Interspeech 2010, Makuhari, Japan, 26-30 September 2010.
  73. Asaei, A, Picart, B., and Bourlard, H. (2010), “Analysis of Phone Posterior Feature Space Exploiting Class-Specific Sparsity and MLP-based Similarity Measure,” IEEE Intl. Conference on Acoustics, Speech, and Signal Processing (ICASSP 2010), Dallas, March 14-19, 2010.
  74. Parthasarathi, S.H.K., Magimai-Doss, M., Bourlard, H., and Gatica-Perez, D. (2010), “Evaluating the Robustness of Privacy-Sensitive Audio Features for Speech Detection in Personal Audio Log Scenarios”, IEEE Intl. Conference on Acoustics, Speech, and Signal Processing (ICASSP 2010), Dallas, March 14-19, 2010.
  75. Garau, G. and Bourlard, H. (2010), “Using Audio and Visual Cues for Speaker Diarization Initialisation”, IEEE Intl. Conference on Acoustics, Speech, and Signal Processing (ICASSP 2010), Dallas, March 14-19, 2010.
  76. Vijayasenan, D., Valente, F., and Bourlard, H. (2010), “Multi-stream Speaker Diarization Beyond Two Acoustic Feature Streams,” IEEE Intl. Conference on Acoustics, Speech, and Signal Processing (ICASSP 2010), Dallas, March 14-19, 2010.
  77. Weifeng Li, A. Billard, and H. Bourlard, “Keyword Detection for Spontaneous Speech,” Proc. the 2nd International Conference on Image and Signal Processing (CISP 2009), Tianjin, China, 17-19 October 2009.
  78. Vijayasenan, D., Valente, F., and Bourlard, H. (2009), “KL Realignment for Speaker Diarization with Multiple Streams,” Interspeech 2009, Brighton (UK), 6-10 September 2009.
  79. Parthasarathi, S.R.K., Magimai-Doss, M., and Bourlard, H. (2009), “Investigating Privacy-Sensitive Features for Speech Detection in Multiparty Conversations,” Interspeech 2009, Brighton (UK), 6-10 September 2009.
  80. Parthasarathi, S.H.K., Magimai-Doss, M., Gatica-Perez, D., and Bourlard, H. (2009), “Speaker Change Detection with Privacy-Preserving Audio Cues”, Proceedings of the ICMI-MLMI Workshop, Cambridge, MA, USA, Nov.2-6, 2009.
  81. Garau, G., Bourlard, H., and Odobez, J.-M. (2009), “'Investigating the use of Visual Focus of Attention for Audio-Visual Speaker Diarisation,” ACM Multimedia 2009, Beijing, Oct. 19-24, 2009.
  82. Li, W., Dines, J., Magimai-Doss, M., and Bourlard, H. (2009), “Non-Linear Mapping for Multi-Channel Speech Separation and Robust Overlapping Speech Recognition,” IEEE Intl. Conference on Acoustics, Speech, and Signal Processing (ICASSP 2009), Taipei, Taiwan, 19-24 April 2009.
  83. Aradilla, G., Bourlard, H., and Magimai-Doss, (2009), “Posterior Features Applied to Speech Recognition Tasks with User-Defined Vocabulary,” IEEE Intl. Conference on Acoustics, Speech, and Signal Processing (ICASSP 2009), Taipei, Taiwan, 19-24 April 2009.
  84. Vijayasenan, D., Valente, F. and Bourlard, H. (2009), “Mutual Information Based Channel Selection for Speaker Diarization of Meeting data,” IEEE Intl. Conference on Acoustics, Speech, and Signal Processing (ICASSP 2009), Taipei, Taiwan, 19-24 April 2009.
  85. Vinciarelli, A, Pantic, M., Bourlard, H., and Pentland, A. (2008), “Social Signal Processing: A Survey on Nonverbal Behavior Analysis in Social Interactions,” ACM Multimedia 2008, Oct.27-Nov.1, Vancouver, BC, Canada.
  86. Li, W., Kumatani, K., Dines, J., Magimai-Doss, and Bourlard, H. (2008), “A Neural Network based Regression Approach for Recognizing Simultaneous Speech,” 5th Joint Workshop on Machine Learning and Multimodal Interaction (MLMI’08), Utrecht, The Netherlands, 8-10 September, 2008.
  87. Li, W., Dines, J., Magimai-Doss, M., and Bourlard, H. (2008), “Neural Network Based Regression for Robust Overlapping Speech Recognition using Microphone Arrays,’’ Interspeech 2008, Brisbane, Australia, 22-16 September 2008.
  88. Vijayasenen, D., Valente, F, and Bourlard, H. (2008), “Integration of TDOA Features in Information Bottleneck Framework for Fast Speaker Diarization,’’ Interspeech 2008, Brisbane, Australia, 22-16 September 2008.
  89. Aradilla, G., Bourlard, H., and Magimai Doss, M. (2008), “Using KL-based Acoustic Models in Large Vocabulary Recognition Tasks,’’ Interspeech 2008, Brisbane, Australia, 22-16 September 2008.
  90. Li, W., Magimai-Doss, M., Dines, J., and Bourlard, H. (2008), “MLP-based Log Spectral Energy Mapping for Robust Overlapping Speech Recognition,” Proceedings of EUSIPCO’2008 (16th European Signal Processing Conference), August 25-29, Lausanne, Switzerland.
  91. Renals, S., Hain, T., and Bourlard, H. (2008), “Interpretation of Multiparty Meetings: The AMI and AMIDA projects”, invited paper, IEEE joint workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA 2008), Trento (Italy), May 6-8, 2008.
  92. Bourlard, H. and Renals, S. (2008), “Recognition and Understanding of Meetings: Overview of the European AMI and AMIDA Projects”, invited talk, Proc. of the LangTech 2008 Workshop, Rome, 28-29 February 2008.
  93. Ketabdar, H. and Bourlard, H. (2008), “Implicit Integration of Phonetic and Lexical Knowledge in Phone Posterior Estimation”, accepted to IEEE Intl. Conference on Acoustics, Speech, and Signal Processing (ICASSP’08), Las Vegas, March 30-April 4, 2008.
  94. Vijayasenan, D., Valente,F., and Bourlard, H., “Combination of Agglomerative and Sequential Clustering for Speaker Diarization”, accepted to IEEE Intl. Conference on Acoustics, Speech, and Signal Processing (ICASSP’08), Las Vegas, March 30-April 4, 2008.
  95. Renals, S., Hain, T., and Bourlard, H. (2007), “Recognition and Understanding of Meetings: the AMI and AMIDA Projects”, Proc. of the IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU’07), invited talk, Kyoto, December 9-13, 2007.
  96. Vijayasenan, D., Valente, F., and Bourlard, H., “Agglomerative Information Bottleneck for Speaker Diarization of Meetings Data”, Proc. of the IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU’07), Kyoto, December 9-13, 2007.
  97. Li, W and Bourlard, H. (2007), “Non-Linear Spectral Contrast Stretching for In-Car Speech Recognition”, Proceedings of Interspeech’2007, 27-31 August 2007, Antwerp, Belgium.
  98. Katebdar, H. and Bourlard, H., “In-Context Phone Posteriors as Complementary Features for Tandem ASR”, Proceedings of Interspeech’2007, 27-31 August 2007, Antwerp, Belgium.
  99. A. Jaimes, H. Bourlard, and S, Renals, “Recording, Indexing, Summarizing, and Accessing Meeting Videos: An Overview of the AMI Project,” invited paper at the 14th International Conference on Image Analysis and Processing (ICIAP’07), 10-14 September 2007, Modena.
  100. Aradilla, G., Vepa. J., and Bourlard, H. (2007), “An Acoustic Model based on Kullback-Leibler Divergence for Posterior Features”, Proceedings of IEEE Intl. Conference on Acoustics, Speech, and Signal Processing (ICASSP), Honolulu, Hawaii, 15-20 April 2007.
  101. Ketabdar, H, Vepa, J., Bengio, S., and Bourlard, H. (2006), “Posterior Based Keyword Spotting with a Priori Thresholds”, Proceedings of Interspeech’2006, Pittsburgh (US-PA), 17-21 September 2006.
  102. Misra, H, Vepa, J., and Bourlard, H. (2006), “Multi-Stream ASR: An Oracle Perspective”, Proceedings of Interspeech’2006, Pittsburgh (US-PA), 17-21 September 2006.
  103. Aradilla, G., Vepa, J., and Bourlard, H. (2006), “Using Posterior-Based Features and Distances in Template Matching for Speech Recognition”, Proceedings of Interspeech’2006, Pittsburgh (US-PA), 17-21 September 2006.
  104. Ketabdar, H., Vepa, J., Bengio, S., and Bourlard, H. (2006), “Using More Informative Posterior Probabilities for Speech Recognition,” Proceedings of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), pp. I.29-32, Toulouse, May 15-19, 2006.
  105. Aradilla, G., Vepa, J., and Bourlard, H. (2006), “Using Pitch as Prior Knowledge in Template-Based Speech Recognition,” Proceedings of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), pp. I.445-448, Toulouse, May 15-19, 2006.
  106. Lathoud, G., Magimai-Doss, M., and Bourlard, H. (2006), “Threshold Selection for Unsupervised Detection, with Application to Microphone Array,” Proceedings of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), pp. III.285-288, Toulouse, May 15-19, 2006.
  107. Lathoud, G., Magimai-Doss, M., Mesot, B., and Bourlard, H. (2005), “Unsupervised Spectral Subtraction for Robust Noise-Robust ASR”, in Proceedings of the Workshop on Automatic Speech Recognition and Understanding (ASRU’05), pp. 343-348, Puerto Rico, Nov.28-Dec.1, 2005.
  108. Bengio, S. and Bourlard, H. (2005), “Multi-Channel Sequence Processing,” invited paper, Proceedings of the Intl. Workshop on “Deterministic and Statistical Methods in Machine Learning”, Sheffield, September 2004 (LNAI 3635, Springer, 2005), pp. 22-36, 2005
  109. Kedabdar, H, Bourlard, H., and Bengio, S. (2005) “Hierarchical Multi-Stream Posterior-based Speech Recognition System”, Proceedings of Intl. Workshop on Machine Learning for Multimodal Interaction (MLMI’05), Lecture Notes in Computer Sciences (LNCS), Springer (ISBN 5-540-32549-2, 2006), pp. 294- 306, Edinburgh, 11-13 July, 2005.
  110. Tyagi, V., Wellekens, C., and Bourlard, H. (2005), “A Variable-Scale Piecewise Stationary Spectral Analysis Technique Applied to ASR”, Proceedings of Intl. Workshop on Machine Learning for Multimodal Interaction (MLMI’05), Lecture Notes in Computer Sciences (LNCS), Springer (ISBN 5-540-32549-2, 2006), pp. 274-284, Edinburgh, 11-13 July, 2005.
  111. Kedabdar, H., Vepa, J., Bengio, S., and Bourlard, H. (2005) “Developing and Enhancing Posterior Based Speech Recognition Systems”, Proceedings of Interspeech’05, Lisbon, 6-9 September 2005.
  112. Aradilla, G., Vepa, J., and Bourlard, H. (2005) “Improving Speech Recognition Using a Data-Driven Approach”, Proceedings of Interspeech’05, Lisbon, 6-9 September 2005.
  113. Misra, H. and Bourlard, H. (2005) “Spectral Entropy Features in Full-Combination Multi-Stream for Robust ASR”, Proceedings of Interspeech’05, Lisbon, 6-9 September 2005.
  114. Tyagi, V., Wellekens, C., and Bourlard, H. (2005) “On Variable-Scale Piecewise Stationary Spectral Analysis of Speech Signals”, Proceedings of Interspeech’05, Lisbon, 6-9 September 2005.
  115. Misra, H., Ikbal, S., Sivadas, S., Bourlard, H., and Hermansky, H. (2005) “Multi-Resolution Spectral Entropy Feature for Robust ASR,” Proceedings of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), pp. I.253-256, Philadelphia (PA), 19-23 March, 2005.
  116. Ikbal, S., Bourlard, H., andMagimai.-Doss, M. (2005) “HMM/ANN based Spectral Peak Location Estimation for Noise Robust Speech recognition,” Proceedings of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), pp. I.453-456, Philadelphia (PA), 19-23 March, 2005.
  117. Bourlard, H., Bengio, S., Magimai Doss, M., Zhu, Q., Mesot, B., and Morgan, N. (2004), “Towards Using Hierarchical Posteriors for Flexible Automatic Speech Recognition Systems”, Proceedings of the DARPA EARS (Effective, Affordable, Reusable, Speech-to-text) Rich Transcription (RT’04) Workshop,7-10 November 2004, IBM Palisades, NY.
  118. BenZeghiba, M.F and Bourlard, H. (2004) “Posteriori Probabilities and Likelihoods Combination for Speech and Speaker Recognition”, Proceedings Intl. Conf on Spoken Language Processing (ICSLP), Jeju Island, Korea, Oct.4-8, 2004.
  119. Ajmera, J., McCowan, I, Bourlard, H, “An online audio indexing system”, Proceedings of Intl. Conf on Spoken Language Processing (ICSLP), Jeju Island, Korea, Oct.4-8, 2004.
  120. Magimai.-Doss, M., Stephenson, T., Ikbal, S. and Bourlard, H. (2004) “Modelling Auxiliary Features in Tandem Systems,” Proc. of Intl. Conference on Spoken Language Processing (ICSLP), Jeju Island, Korea, Oct.4-8, 2004.
  121. Ikbal, S., Misra, H., Sivadas, S., Hermansky, H., and Bourlard, H. (2004) “Entropy based combination of Tandem representations for noise robust ASR”, Proc. of Intl. Conference on Spoken Language Processing (ICSLP), Jeju Island, Korea, Oct.4-8, 2004.
  122. Ikbal, S., Magimai.-Doss, M., Misra, H., and Bourlard, H. (2004) “Spectro-temporal activity pattern (STAP) features for noise robust ASR”, Proc. of Intl. Conference on Spoken Language Processing (ICSLP), Jeju Island, Korea, Oct.4-8, 2004.
  123. Bourlard, H., McCowan, I., Gatica-Perez, D., Bengio, S., and Moore, D. (2004), “Modeling Human Interactions in Meetings based on Audio and Visual Information,” invited talk, Proc. of Special Workshop in Maui (SWIM), Lectures by Masters in Speech Processing, Maui, Hawaii, January 12-14. 2004.
  124. Hermansky, H., and Bourlard, H. (2004), “Some Emerging Concepts in Speech Recognition,”, invited talk, Proc. of Special Workshop in Maui (SWIM), Lectures by Masters in Speech Processing, Maui, Hawaii, January 12-14. 2004.
  125. Magimai-Doss, M., Bengio, S., and Bourlard, H. (2004), “Joint Decoding for Phoneme-Grapheme Continuous Speech Recognition,” Proceedings of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Montreal, May 17-21, 2004.
  126. Misra, H., Ikbal, S., Bourlard, H., and Hermansky, H. (2004) “Spectral Entropy Based Feature for Robust ASR,” Proceedings of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Montreal, May 17-21, 2004.
  127. BenZeghiba, M. and Bourlard, H. (2004) “Confidence Measures in Multiple Pronunciations Modeling for Speaker Verification,” Proceedings of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Montreal, May 17-21, 2004.
  128. Ikbal, S., Misra, H., Bourlard, H., and Hermansky, H. (2004) “Phase Autocorrelation (PAC) Features in Entropy Based Multi-Stream for Robust Speech Recognition,” Proceedings of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Montreal, May 17-21, 2004.
  129. Tyagi, V., McCowan, I., Misra, H., and Bourlard, H. (2003) “Cepstral Filtering Based Features for Robust ASR,” Proceedings of IEEE Automatic Speech Recognition and Understanding (ASRU 2003), St. Thomas, U.S. Virgin Islands, Nov.30-Dec.3, 2003.
  130. Magimai-Doss, M., Stephenson, T., Bourlard, H., Bengio, S., and Hermansky, H. (2003) “Automatic Speech Recognition Using Graphemes as Auxiliary Information,” in Proceedings of IEEE Automatic Speech Recognition and Understanding (ASRU 2003), St. Thomas, U.S. Virgin Islands, Nov.30-Dec.3, 2003.
  131. Ikbal, S., Bourlard, H., and Hermansky, H. (2003) “Nonlinear Spectral Transformations for Robust Speech Recognition,” in Proceedings of IEEE Automatic Speech Recognition and Understanding (ASRU 2003), St. Thomas, U.S. Virgin Islands, Nov.30-Dec.3, 2003.
  132. Tyagy, V., McCowan, I., Bourlard, H., Misra, H. (2003) “On Factoring Speech Dynamics for Robust Speech Recognition,” in Proceedings of Eurospeech’2003, Geneva, Sep.1-4, 2003.
  133. BenZeghiba, M.F. and Bourlard, H. (2003) “On the combination of speech and speaker recognition”, in Proceedings of Eurospeech’2003, Geneva, Sep.1-4, 2003.
  134. Magimai-Doss, M., Stephenson, T.A., and Bourlard, H. (2003) “Using pitch frequency information as speech recognition,” in Proceedings of Eurospeech’2003, Geneva, Sep.1-4, 2003.
  135. Sanderson, C., Bengio, S., Bourlard, H., Mariethoz, J., Collobert, R., BenZeghiba, M., Cardinaux, F., and Marcel, S. (2003) “Speech and face based biometric authentication at IDIAP,” in Proceedings of IEEE Intl. Conf. on Multimedia and Expo (ICME’2003), Baltimore, July 2003.
  136. Gatica-Perez, D., McCowan, I., Barnard, M., Bengio, S., and Bourlard, H. (2003) “On automatic annotation of meeting databases,” in Proceedings of Intl. Conf. on Image Processing (ICIP), 2003.
  137. McCowan, I., Gatica-Perez, D., Bengio, S., Wellner, P., Moore, D., Lathoud, G., Monay, F., and Bourlard, H. (2003), “Modeling Human Interaction in Meetings,” Proceedings of the IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICAASP), special session on “Smart Meeting Rooms”, Hong-Kong, pp. IV.748-751, May 2003.
  138. BenZeghiba, M. and Bourlard, H. (2003) “Hybrid HMM/ANN and GMM Combination for User-Customized Password Speaker Verification,” Proceedings of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Hong-Kong, pp. II.225-228, May 2003.
  139. Stephenson, T., Magimai-Doss, M., and Bourlard, H. (2003) “Speech Recognition of Spontaneous, Noisy Speech Using Auxiliary Information in Bayesian Networks,” Proceedings of the IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Hong-Kong, pp. I.20-23, May 2003.
  140. Ikbal, S., Misra, H., and Bourlard, H. (2003) “Phase Autocorrelation (PAC) Derived Robust Speech Features,” Proceedings of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Hong-Kong, pp. II.133-136, May 2003.
  141. Misra, H., Bourlard, H., and Tyagi, V. (2003) “Entropy-Based Full-Combination Multi-Stream ASR,” accepted to IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Hong-Kong, May 2003.
  142. BenZeghiba, M. and Bourlard, H. (2003) “User Customized Password HMM Based Speaker Verification,” in Proceedings of the COST-275 Workshop on The Advent of Biometrics on the Internet, Rome, Italy, pp. 103-106, November 7-8, 2002.
  143. Ikbal, S., Weber, K., and Bourlard, H. (2002) “Speaker Normalization using HMM2,” in Proceedings of IEEE Workshop on Neural Networks for Signal Processing (NNSP'02), pp. 647-656, Martigny (Switzerland), Sep. 4-6, 2002.
  144. Stephenson, T., Escofet, J., Magimai-Doss, M., and Bourlard, H. (2002) “Dynamic Bayesian Network Based Speech Recognition with Pitch and Energy as Auxiliary Variables,” in Proceedings of IEEE Workshop on Neural Networks for Signal Processing (NNSP'02), pp. 637-646, Martigny (Switzerland), Sep. 4-6, 2002.
  145. Morris, A., Payne, S., and Bourlard, H. (2002) “Low Cost Duration Modelling for Noise Robust Speech Recognition,” accepted to Intl. Conf. of Spoken Language Processing (ICSLP'02), pp. 1025-1028, Denver, September 2002.
  146. Ajmera, J., Bourlard, H., Lapidot, I., and McCowan, I. (2002) “Unknown-Multiple Speaker Clustering using HMM,” Proceedings of Intl. Conf. of Spoken Language Processing (ICSLP'02), pp. 573-576, Denver, September 2002.
  147. Marsal Pujol, P., Pol Font, S., Hagen, A., and Bourlard, H. (2002) “Comparison and Combination of Rasta-PLP and FF Features in a Hybrid HMM/MLP Speech Recognition System,” Proceedings of Intl. Conf. of Spoken Language Processing (ICSLP'02), pp. 1057-1060, Denver, September 2002.
  148. BenZeghiba, M. and Bourlard, H. (2002) “User-Customized Password Verification based on HMM/ANN and GMM Models,” Proceedings of Intl. Conf. of Spoken Language Processing (ICSLP'02), pp. 1325-1328, Denver, September 2002.
  149. McCowan, I., Morris, A., and Bourlard, H. (2002) “Improving Speech Recognition Performance of Small Microphone Arrays Using Missing Data Techniques,” Proceedings of Intl. Conf. of Spoken Language Processing (ICSLP'02), pp. 2181-2184, Denver, September 2002.
  150. Stephenson, T., Magimai-Doss, M. and H. Bourlard, H. (2002) “Auxiliary Variables in Conditional Gaussian Mixtures for Automatic Speech Recognition,” Proceedings of Intl. Conf. of Spoken Language Processing (ICSLP'02), pp. 2665-2668, Denver, September 2002.
  151. Weber, K., de Wet, F., Boves, L., Bengio, S., and Bourlard, H. (2002) “Evaluation of Formant-Like Features for ASR”, Proceedings of Intl. Conf. of Spoken Language Processing (ICSLP'02), pp. 2101-2104, Denver, September 2002.
  152. Bourlard, H., “Some Recent Advances in Speech Recognition with Potential Applications in Other Statistical Pattern Recognition Areas,” Proc. of the Intl. Conference on Pattern Recognition (ICPR, invited plenary talk), page III-727, Québec, 11-15 August 2002.
  153. Chen, D., Odobez, J.-M., and Bourlard, H. (2002), “Text Segmentation and Recognition in Complex Background Based on Markov Random Field,” Proc. of the Intl. Conference on Pattern Recognition (ICPR), pp. IV.227-230, Québec, 11-15 August 2002.
  154. Stephenson T.A., Magimai-Doss M., Bourlard, H. (2002), “Mixed Bayesian Networks with Auxiliary Variables for Automatic Speech Recognition,” Proc. of the Intl. Conference on Pattern Recognition (ICPR), pp. IV.293-296, Québec, 11-15 August 2002.
  155. Weber, K., Bengio, S., and Bourlard, H. (2002), “Increasing Speech Recognition Robustness with HMM2,” in Proceedings of IEEE Intl. Conference on Acoustics, Speech, and Signal Processing (ICASSP’2002), Orlando, Florida, pp. I.929-932, May 13-17, 2002.
  156. McCowan, I. and Bourlard, H. (2002) “Microphone Array Post-Filter for Diffuse Noise Field,” in Proceedings of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP’2002), Orlando, Florida, pp. I.905-908, May 13-17, 2002.
  157. Ajmera, J., McCowan, I., and Bourlard, H. (2002) “Robust HMM-Based Speech/Music Segmentation,” in Proceedings of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP’2002), Orlando, Florida, pp. I.297-300, May 13-17, 2002.
  158. Chen, D., Bourlard, H., and Thiran, J.-P. (2001) “Text Identification in Complex Background Using SVM,” in Proceedings of Proc. of the Intl. Conf. on Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 621-626, December 2001.
  159. Chen, D, Shearer, K, and Bourlard H. (2001) “Video OCR for Sport Video Annotation and Retrieval,” in Proc. of the 9th IEEE Intl. Conf. on Mechatronics and Machine Vision in Practice, Aug.27, 2001.
  160. Chen, D., Shearer, K., and Bourlard, H. (2001) “Text Enhancement with Asymmetric Filter for Video OCR,” in Proc. of the 11th IEEE Intl. Conference on Image Analysis and Processing (ICIAP), pp. 192-198, September 2001.
  161. Morris, A., Hagen, A., and Bourlard, H., “MAP Combination of Multi-Stream HMM or HMM/ANN Experts,” Proceedings of Eurospeech'2001, Aalborg, Denmark, Sep. 3-7, 2001.
  162. Hagen, A. and Bourlard, H. (2001), “Error Correcting Posterior Combination for Multi-Band Speech Recognition,” Proceedings of Eurospeech'2001, Aalborg, Denmark, Sep. 3-7, 2001.
  163. Stephenson, T., Mathew, A., and Bourlard, H. (2001), “Modeling Auxiliary Information in Bayesian Network based ASR,” Proceedings of Eurospeech'2001, Aalborg, Denmark, Sep. 3-7, 2001.
  164. Weber, K., Bengio, S., and Bourlard, H. (2001), “HMM2--Extraction of Formant Structures and Their Use for Robust ASR,” Proceedings of Eurospeech'2001, Aalborg, Denmark, Sep. 3-7, 2001.
  165. Morris, A., Barker, J., and Bourlard, H., “From missing data to maybe useful data: soft data modelling for noise robust ASR,” Proceedings of Workshop on Innovation in Speech Processing, Stratford-upon-Avon, UK, April 2-3, 2001.
  166. Hagen, A., Bourlard, H., and Morris, A. (2001), “Adaptive ML-Weighting in Multi-Band Recombination of Gaussian Mixture ASR,” Proceedings of IEEE Intl. Conf. On Acoustics, Speech, and Signal Processing (ICASSP'2001), Salt-Lake City, 2001.
  167. Van Kommer R., Rajman, M., and Bourlard, H. (2000), “Heading Towards Virtual-Commerce Portals,” ComTec Journal, September 2000, pp. 9-12.
  168. Bourlard, H., Bengio, S, and Weber, K., “New Approaches Towards Robust and Adaptive Speech Recognition,” Invited Keynote, Proceedings of Advanced Neural Information Processing Systems (NIPS 13) workshop, T.K. Leen, T.G. Dietterich, and V. Tresp (Eds.), MIT Press, Denver (CO), Nov. 27-Dec. 2, 2000.
  169. Hagen, A, Morris, A., and Bourlard, H., “From Multi-Band Full Combination to Multi-Stream Full Combination Processing in Robust ASR,” Proc. of ISCA ITRW Intl. Workshop on Automatic Speech Recognition: Challenges for the Next Millennium, Paris, Sep. 18-20, 2000.
  170. Weber, K., Bengio, S., and Bourlard, H., “HMM2: A Novel Approach to HMM Emission Probability Estimation,” Intl. Conf. on Spoken Language Processing (ICSLP'00) (Beijing, China), pp. III-147-150, Nov. 2000.
  171. Stephenson, T., Bourlard, H., Bengio, S., and Morris, A., “Automatic Speech Recognition using Dynamic Bayesian Networks with both Acoustic and Articulatory Features,” Intl. Conf. on Spoken Language Processing (ICSLP'00) (Beijing, China), pp. II-951-954, Nov. 2000.
  172. Hagen, A. and Bourlard, H., “Using Multiple Time Scales in the Framework of Multi-Stream Speech Recognition,” Intl. Conf. on Spoken Language Processing (ICSLP'00) (Beijing, China), pp. I-349-352, Nov. 2000.
  173. Morris, A., Josifovski, L., Bourlard, H., Cooke, M., and Green, P., “A Neural Network for Classification with Incomplete Data: Applications to Robust ASR,” Intl. Conf. on Spoken Language Processing (ICSLP'00) (Beijing, China), pp. I-409-412, Nov. 2000.
  174. Moeller, S. and Bourlard, H. (2000), “Real-Time Telephone Transmission Simulation for Speech Recognizer and Dialogue System Evaluation and Improvement,” Intl. Conf. on Spoken Language Processing (ICSLP'00) (Beijing, China), pp. 750-753, Nov. 2000.
  175. Bernardis, G., Bourlard, H., Rajman, M., and Chapellier, J.-C., “Development of Acoustic and Linguistic Resources for Research and Development in Interactive Vocal Information Servers,” Intl. Conf. on Language Resources and Evaluation, (Athens, Greece), 31 May-2 June, 2000.
  176. Silaghi, M.-C., Bourlard, H. (2000), “A New Keyword Spotting Approach based on Iterative Dynamic Programming,” Proc. of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (Istanbul, Turkey), pp. III-1831-1834, June 5-9, 2000.
  177. Silaghi, M.-C., Bourlard, H. (1999), “Iterative Posterior-Based Keyword Spotting Without Filler Models,” Proceedings of the IEEE Automatic Speech Recognition and Understanding (ASRU'99) Workshop}, Keystone, Colorado, Dec. 12-15, 1999.
  178. Morris, A., Hagen, A., and Bourlard, H. (1999), “The Full Combination Sub-Bands Approach to Noise Robust HMM/ANN Based ASR,” Proceedings of EUROSPEECH'99 (Budapest), pp. 599-602, September 1999.
  179. Hagen, H., Morris, A., and Bourlard, H. (1999), “Different Weighting Schemes in the Full Combination Sub-band Approach for Noise Robust ASR,” Proc. of the ESCA Workshop on Robust Methods for Speech Recognition in Adverse Conditions (Tampere, Finland), pp. 199-202, May 1999.
  180. Bourlard, H. (1999), “Non-Stationary Multi-Channel (Multi-Stream) Processing Towards Robust and Adaptive ASR,” Invited Keynote, Proc. of the ESCA Workshop on Robust Methods for Speech Recognition in Adverse Conditions (Tampere, Finland), pp. 1-10, May 1999.
  181. Glotin, H., Berthommier, F., Tessier, E., and Bourlard, H. (1998), “Interfacing CASA and Multi-Band Speech Recognition,” Proceedings of Intl. Conf. on Spoken Language Processing (Sydney, Australia), pp. 1415-1418.
  182. Bernardis, G., and Bourlard, H. (1998), “Improving Posterior-Based Confidence Measures in Hybrid HMM/ANN Speech Recognition Systems,” Proceedings of Intl. Conf. on Spoken Language Processing (Sydney, Australia), pp. 775-778.
  183. Glotin, H., Berthommier, F., Tessier, E., and Bourlard, H. (1998), “Interfacing of CASA and Multistream Recognition,” Proceedings of Workshop on Text, Speech and Dialog (TSD'98) (Brno, Czech Republic, September 1998), pp. 207-212.
  184. Bernardis, G., and Bourlard, H. (1998), “Confidence Measures in Hybrid HMM/ANN Speech Recognition,” Proceedings of Workshop on Text, Speech and Dialog (TSD'98) (Brno, Czech Republic, September 1998), pp. 159-164.
  185. Glotin, H., Tessier, E., Bourlard, H., and Berthommier, F. (1998). “Reconnaissance Multi-Bandes de la Parole Bruitée par Couplage Entre Niveaux Primitifs et d'Identification,” Proc. XXIIèmes Journées d'Etude sur la Parole (Martigny, Suisse, June 1998), pp. 375-378.
  186. Glotin, H., Tessier, E., Bourlard, H., and Berthommier, F. (1998). “Reconnaissance Robuste de la Parole par Segmentation Signal/Bruit en Sous-Bandes,” Neurosciences et Sciences de l'Ingénieur'98 (Munster, CNRS, France, May 1998).
  187. Bourlard, H. (1997), “State-of-the-Art and Recent Progress in Hybrid HMM/ANN Speech Recognition,” Proc. of the Intl. Conf. on Artificial Neural Networks (Lausanne, Switzerland, Oct. 8-10), Springer (ISBN 3-540-63631-5), pp. 875-884.
  188. Dupont, S. and Bourlard, H. (1997), “Using Multiple Time Scales in a Multi-Stream Speech Recognition System,” Proceedings of EUROSPEECH'97 (Rhodes, Greece, Sep. 1997), pp. 3-6.
  189. Hennebert, J., Ris, C., Bourlard, H., Renals, S., and Morgan, N. (1997), “Estimation of Global Posteriors and Forward-Backward Training of Hybrid HMM/ANN Systems,” Proceedings of EUROSPEECH'97 (Rhodes, Greece, Sep. 1997), pp. 1951-1954.
  190. Dupont, S., Bourlard, H., Deroo, O., Fontaine, V., and Boite, J.-M. (1997), “Hybrid HMM/ANN Systems for Training Independent Tasks: Experiments on 'Phonebook' and Related Improvements,” Proc. of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (Munich, Germany, April 1997), pp. 1767-1770.
  191. Bourlard, H. and Dupont, S. (1997), “Subband-Based Speech Recognition,” Proc. of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (Munich, Germany, April 1997), pp. 1251-1254.
  192. Fontaine, V. and Bourlard, H. (1997), “Speaker-Dependent Speech Recognition Based on Phone-Like Unit Model -- Application to Voice Dialing,” Proc. of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (Munich, Germany, 21-24 April 1997), pp. 1527-1530.
  193. Dupont, S., Bourlard, H., and Ris, C. (1997), “Robust Speech Recognition based on Multi-Stream Features,” Proc. of the ESCA-NATO Workshop on Robust Speech Recognition for Unknown Communication Channels} (Pont-à-Mousson, France, 17-18 April 1997), pp. 95-98.
  194. Bourlard, H. (1996), “Neural Networks --- Theory and Parallels with Conventional Algorithms,” Proc. Neural Networks Summer School, University of Cambridge, Cambridge Programme for Industry, Dept. of Engineering, UK, 9-12 Sep. 96.
  195. Dupont, S. and Bourlard, H. (1996). “Multiband Approach for Speech Recognition,” Proc. of the ProRISC/IEEE Workshop on Circuits, Systems, and Signal Processing (Mierlo, The Netherlands, 27-28 Nov. 1996), pp. 113-118.
  196. Bourlard, H. and Dupont, S. (1996), “A New ASR Approach Based on Independent Processing and Recombination of Partial Frequency Bands,” Proc. of Intl. Conf. on Spoken Language Processing (ICSLP) (Philadelphia, 3-6 Oct. 1996), pp. 426-429.
  197. Bilmes, J., Morgan, N., Wu, S.-L., and Bourlard, H. (1996), “Stochastic Perceptual Speech Models with Durational Dependence,” Proc. of Intl. Conf. on Spoken Language Processing (ICSLP)} (Philadelphia, 3-6 Oct. 1996), pp. 1301-1304.
  198. Bourlard, H. (1996), “Reconnaissance Automatique de la Parole: Modélisation ou Description?” Actes des XXIèmes Journées d'Etude sur la Parole (JEP), Plenary Talk, pp. 263-272, Avignon (France, June 1996).
  199. Bourlard, H. (1996), “Copernicus and the ASR Challenge -- Waiting for Kepler,” Invited Talk, Proceedings of DARPA Speech Recognition Workshop, Arden House, NY, pp. 157-162, Feb. 18-21, 1996.
  200. Bourlard, H., Dupont, S., Hermansky, H., and Morgan, N. (1996), “Towards Subband-Based Speech Recognition,” Proc. VIII European Signal Processing Conference (EUSIPCO'96) (Trieste, Italy), pp. 1579-1582, Sep. 10-13, 1996.
  201. Bourlard, H., Konig, Y., Morgan, N., and Ris, C. (1996), “A New Training Algorithm for Hybrid HMM/ANN Speech Recognition Systems,” Proceedings of VIII European Signal Processing Conference (EUSIPCO'96) (Trieste, Italy), pp. 101-104, Sep. 10-13, 1996.
  202. Konig, Y., Bourlard, H., and Morgan, H. (1996), “REMAP --- Experiments with Speech Recognition,” Proc. of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (Atlanta, GA), pp. VI: 3350-3353, May 7-10, 1996.
  203. Morgan, N., Konig, Y., Wu, S.-L., and Bourlard, H. (1995), “Transition-Based Statistical Training for ASR,” Proc. of IEEE Workshop on Automatic Speech Recognition (Snowbird, UT), Dec. 1995.
  204. Bourlard, H. (1995), “New Developments in the Use of Markov Models and Artificial Neural Networks for Speech Recognition,” Invited Talk, Proceedings of Intl. Conf. on Artificial Neural Networks (ICANN'95)} (Paris, France), vol. 1, pp. 231-239, Oct. 9-13, 1995.
  205. Bourlard, H., Konig, Y., and Morgan, N. (1995), “REMAP: Recursive Estimation and Maximization of A Posteriori Probabilities in Connectionist Speech Recognition,” Proceedings of EUROSPEECH'95 (Madrid, Spain), pp. 1663-1666, September 1995.
  206. Bourlard, H. (1995), “Towards Increasing Speech Recognition Error Rates,” Invited Keynote Speech, Proceedings of EUROSPEECH'95 (Madrid, Spain), pp. 883-894, Sep. 1995.
  207. Morgan, N., Wu, S.-L., and Bourlard, H. (1995), “Digit Recognition with Stochastic Perceptual Models of Speech,” Proceedings of EUROSPEECH'95 (Madrid, Spain), pp. 771-774, Sep. 1995.
  208. Bourlard, H. (1995), “Neural Networks---Theory and Parallels with Conventional Algorithms,” Proc. Neural Networks Summer School, University of Cambridge, Cambridge Programme for Industry, Dept. of Engineering, UK, July 1995.
  209. Morgan, N., Bourlard, H., Greenberg, S., Hermansky, H., and Wu, S.-L. (1995), “Stochastic Perceptual Models of Speech,” Proc. of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (Detroit, MI), pp. 397-400.
  210. Bourlard, H., Konig, Y., and Morgan, N. (1994), “REMAP: Recursive Estimation and Maximization of A Posteriori Probabilities --- Application to Transition-Based Connectionist Speech Recognition,” ICSI Technical Report TR-94-064, Intl. Computer Science Institute, Berkeley, CA.
  211. Mirghafori, N., Morgan, N., and Bourlard, H. (1994), “Parallel Training of MLP Probability Estimators for Speech Recognition: A Gender-Based Approach,” in Proc. of IEEE Workshop on Neural Networks for Signal Processing, J. Vlontzos, J-N. Hwang, and E. Wilson (Eds.), pp. 289-298.
  212. Van Hamme, H., Gallopyn, G., Weynants, L., D'hoore, B., and Bourlard, H. (1994), “Comparison of Acoustic Features and Robustness Tests of a Real-Time Recognizer Using a Hardware Telephone Line Simulator,” Proc. Intl. Conf. on Spoken Language Processing} (Yokohama, Japan), pp. 1907-1910, Sep. 18-22, 1994.
  213. Morgan, N., Bourlard, H., Greenberg, S., and Hermansky, H. (1994), “Stochastic Perceptual Auditory-Event-Based Models for Speech Recognition,” Proc. Intl. Conf. on Spoken Language Processing (Yokohama, Japan), pp. 1943-1946, Sep. 18-22, 1994.
  214. Bourlard, H. (1994), “Neural Networks --- Theory and Parallels with Conventional Algorithms,” Proc. Neural Networks Summer School, University of Cambridge, Cambridge Programme for Industry, Dept. of Engineering, UK.
  215. de Veth, J. and Bourlard, H. (1994), “Comparison of Hidden Markov Model Techniques for Automatic Speaker Verification,” Proc. ESCA Workshop on Automatic Speaker Recognition, Identification and Verification (Martigny, Switzerland), April 5-7, pp. 11-14.
  216. Bourlard, H., D'hoore, B., and Boite, J.-M. (1994), “Optimizing Recognition and Rejection Performance in Wordspotting Systems,” Proc. of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (Adelaide, Australia), pp. I: 373-376.
  217. Boite, J.-M., Bourlard, H., D'hoore, B., Accaino, S., and Vantieghem, J. (1994), “Task Independent and Dependent Training: Performance Comparison of HMM and Hybrid HMM/MLP Approaches,” Proc. of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (Adelaide, Australia), pp. I:617-620.
  218. Saerens, M. and Bourlard, H. (1993), “Linear and Nonlinear Prediction for Speech Recognition with Hidden Markov Models,” Proc. EUROSPEECH'93 (Berlin, Germany), pp. 807-810.
  219. de Veth, J., Gallopyn, G., and Bourlard, H. (1993), “Speaker Verification Over Telephone Channels Based on Concatenated Phonemic Hidden Markov Models,” Proc. EUROSPEECH'93, (Berlin, Germany), pp. 2279-2282.
  220. Robinson, T., Almeida, L., Boite, J.-M., Bourlard, H., Fallside, F., Hochberg, M., Kershaw, D., Kohn, P., Konig, Y., Morgan, N., Neto, J.P., Renals, S., Saerens, M., and Wooters, C. (1993), “A Neural Network Based, Speaker Independent, Large Vocabulary, Continuous Speech Recognition System: The Wernicke Project,” Proc. EUROSPEECH'93 (Berlin, Germany), pp. 1941-1944.
  221. Schmid, P., Cole, R., Fanty, M., Bourlard, H., and Haesen, M. (1993), “Real-Time, Neural Network Based, French Alphabet Recognition with Telephone Speech,” Proc. EUROSPEECH'93 (Berlin, Germany), pp. 1723-1726.
  222. Bourlard, H., Boite, J.-M., D'Hoore, B., and Saerens, M. (1993), “Performance Comparison of Hidden Markov Models and Neural Networks for Task Dependent and Independent Word Recognition,” Proc. EUROSPEECH'93 (Berlin, Germany), pp. 1925-1928.
  223. Boite, J.-M., Bourlard, H., and Haesen, M. (1993), “A New Approach Towards Keyword Spotting,” Proc. EUROSPEECH'93 (Berlin, Germany), pp. 1273-1276.
  224. Bourlard, H. (1993), “Neural Networks --- Theory and Parallels with Conventional Algorithms,” Proc. Neural Networks Summer School, University of Cambridge, Cambridge Programme for Industry, Dept. of Engineering, UK.
  225. de Veth, J., Gallopyn, G., and Bourlard, H. (1993), “Limited Parameter Hidden Markov Models for Random Connected Digit Speaker Verification over Telephone Channels,” Proc. of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (Minneapolis, MI), pp. II:247-250.
  226. Bourlard, H. (1992), “Continuous Speech Recognition: From Hidden Markov Models to Neural Networks,” Invited Keynote Speaker, Proc. EUSIPCO'92, Sixth European Signal Processing Conference (Brussels, Belgium), pp. 63-70.
  227. Bourlard, H. (1992), “Neural Networks---Theory and Parallels with Conventional Algorithms,” Proc. Neural Networks Summer School, University of Cambridge, Cambridge Programme for Industry, Dept. of Engineering, UK.
  228. Bourlard, H. (1992), “La dimension fractale d'une série chronologique implique l'existence d'un prédicteur dont l'ordre est lié à cette dimension,” (“The fractal dimension of a time series implies the existence of a nonlinear predictor, which order is related to this dimension”), Ph.D. Annex Thesis, Faculté Polytechnique de Mons, Belgium, June 1992.
  229. Bourlard, H. (1992), “Reconnaissance Automatique de la Parole: Modèles Stochastiques et/ou Modèles Connexionistes?,” Plenary Talk, Proc. 19èmes Journées d'Etude sur la Parole (Brussels, Belgium), pp. 499-506, May 1992.
  230. Bourlard, H. (1992), “Speech Processing and Neural Networks: A Few Applications,” Proc. IEEE ProRISC Workshop on Circuits, Systems and Signal Processing (Houthalen, Belgium), pp. 17-26.
  231. Bourlard, H. and Morgan, N. (1992), “CDNN: A Context Dependent Neural Network for Continuous Speech Recognition,” Proc. of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (San Francisco, CA), pp. II-349-352.
  232. Renals, S., Morgan, N., Cohen, M., Franco, H., and Bourlard, H. (1992), “Improving Statistical Speech Recognition,” Proc. of IEEE Intl. Joint Conf. on Neural Networks (Baltimore, MD), pp. II:302-307.
  233. Morgan, N., Renals, S., Cohen, M., Franco, H., and Bourlard, H. (1991), “Using Neural Nets in the DECIPHER Speech Recognition System,” Proc. IEEE Workshop on Automatic Speech Recognition (Arden House, NY), Harriman New York.
  234. Bourlard, H. and Morgan, N. (1991), “Neural Networks for Statistical Inference: Generalizations with Applications to Speech Recognition,” Proc. of IEEE Intl. Joint Conf. On Neural Networks (IJCNN) (Singapore), pp. 242-247.
  235. Morgan, N., Bourlard, H., Wooters, C., Kohn, P., and Cohen, M. (1991), “Phonetic Context in Hybrid HMM/MLP Continuous Speech Recognition,” Proc. EUROSPEECH'91 (Genova, Italy), pp.109-112.
  236. Bourlard, H. (1991), “Neural Nets and HMMs: Review and Generalizations,” Invited Keynote Lecture, Proc. EUROSPEECH'91 (Genova, Italy), pp. 363-369.
  237. Morgan, N., Hermansky, H., Bourlard, H., Wooters, C., and Kohn, P. (1991), “Continuous Speech Recognition Using PLP Analysis with Multilayer Perceptrons,” Proc. of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (Toronto, Canada), pp. 49-52.
  238. Bourlard, H. (1991), “Neural Networks--Theory and Parallels with Conventional Algorithms,” Proc. Neural Networks Summer School, University of Cambridge, Cambridge Programme for Industry, Dept. of Engineering, UK, April 1991.
  239. Morgan, N., Wooters, C., Bourlard, H., and Cohen, M. (1990), “Continuous Speech Recognition on the Resource Management Database Using Connectionist Probability Estimation,” Proc. 1990 Intl. Conf. on Spoken Language Processing (Kobe, Japan), pp. 31.1.1-4.
  240. Bourlard, H. (1990), “Continuous Speech Recognition and Connectionist Models,” Invited Paper, Proc. VERBA'90 Intl. Conf. on Speech Technologies (Roma, Italy), pp. 83-90.
  241. Morgan, N. and Bourlard, H. (1990), “Continuous Speech Recognition Using Multilayer Perceptrons with Hidden Markov Models,” Proc. of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (Albuquerque, NM), pp. 413-416.
  242. Bourlard, H. (1989), “Continuous Speech Recognition: Hidden Markov Models vs the Connectionist Hope,” Proc. 23rd IEEE Asilomar Conf. on Signals, Systems and Computers (Pacific Grove, CA), pp. 331-335.
  243. Bourlard, H. and Wellekens, C.J. (1989), Speech Dynamics and Recurrent Neural Networks, Proc. of IEEE Intl. Conf. On Acoustics, Speech, and Signal Processing (Glasgow, Scotland), pp. 33-36.
  244. Wellekens, C.J. and Bourlard, H. (1989), “Les Applications des Modèles Connexionistes en Reconnaissance de la Parole,” Invited Paper, Comptes Rendus des Journées Francophones d'Informatiques (Nancy, France), pp. 181-192, Editions EC2, Nanterre, France.
  245. Bourlard, H. and Wellekens, C.J. (1988), “A Link between Markov Models and Multilayer Perceptrons,” First Annual Meeting of the Intl. Neural Networks Society (INNS) (Boston, MA), Pergamon Press, p. 290.
  246. Bourlard, H. and Wellekens, C.J. (1988), “Neural Network and Applications to Speech Processing (Part II),” Revue HF, vol. XIV, no. 3, pp. 69-80.
  247. Bourlard, H. and Wellekens, C.J. (1988), “Neural Network and Applications to Speech Processing (Part I),” Revue HF, vol. XIV, no. 2, pp. 37-54.
  248. Bourlard, H. and Kamp, Y. (1988), “Auto-Association by Multilayer Perceptrons and Singular Value Decomposition,” Proc. Neural Networks for Computing (Snowbird, UT).
  249. Bourlard, H. and Wellekens, C.J. (1987), “Multilayer Perceptrons and Speech Recognition,” Proc. of IEEE First Intl. Conf. on Neural Networks (San Diego, CA), pp. IV-407-416.
  250. Bourlard, H. and Wellekens, C.J. (1986), “Discriminant Functions for Connected Speech Recognition,” Proc. EUSIPCO'86, European Signal Processing Conference (The Hague, The Netherlands), North-Holland, pp. 1:507-510.
  251. Bourlard, H. and Wellekens, C.J. (1986), “Connected Speech Recognition by Phonemic Semi-Markov Chains for State Occupancy Modeling,” Proc. EUSIPCO'86, European Signal Processing Conference (The Hague, The Netherlands), North-Holland, pp. 1:511-514.
  252. Bourlard, H. (1986), “Automatic Determination of a Phonemic Confusion Matrix and its Use for Connected Speech Recognition,” Proc. EUSIPCO'86, European Signal Processing Conference (The Hague, The Netherlands), North-Holland, pp. 1:569-572.
  253. Bourlard, H. and Wellekens, C.J. (1986), “Connected Speech Recognition by Statistical Methods,” Proceedings of the EURASIP Short Course on Speech Processing (Brussels, Belgium).
  254. Bourlard, H., Kamp, Y., and Wellekens, C.J. (1985), “Speaker Dependent Speech Recognition via Phonemic Markov Models,” Proc. of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (Tampa, FL), pp. 31.5.1-4.
  255. Bourlard, H., Kamp, Y., and Wellekens, C.J. (1985), “Modèles Statistiques de Mots et de Phonèmes pour la Reconnaissance de Phrases,” Actes du Séminaire sur la Quantification Vectorielle pour le Traitement de la Parole (Paris, France), Ed. L. Miclet, ENST, pp. 203-207.
  256. Bourlard, H., Ney, H., and Wellekens, C.J. (1984), “Connected Digit Recognition using Vector Quantization,” Proc. of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (San Diego, CA), pp. 16.10.1-4.