Olivier Siohan

According to our database, Olivier Siohan authored at least 83 papers between 1992 and 2023.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2023

Audio-visual fine-tuning of audio-only ASR models.

Avner May, Dmitriy Serdyuk, Ankit Parag Shah, Otavio Braga, Olivier Siohan

CoRR, 2023

Cascaded encoders for fine-tuning ASR models on overlapped speech.

Richard Rose, Oscar Chang, Olivier Siohan

CoRR, 2023

Conformers are All You Need for Visual Speech Recogntion.

Oscar Chang, Hank Liao, Dmitriy Serdyuk, Ankit Parag Shah, Olivier Siohan

CoRR, 2023

Revisiting the Entropy Semiring for Neural Speech Recognition.

Oscar Chang, Dongseong Hwang, Olivier Siohan

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

On Robustness to Missing Video for Audiovisual Speech Recognition.

Oscar Chang, Otavio Braga, Hank Liao, Dmitriy Serdyuk, Olivier Siohan

Trans. Mach. Learn. Res., 2022

Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition.

Dmitriy Serdyuk, Otavio Braga, Olivier Siohan

CoRR, 2022

Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition for Single and Muti-Person Video.

Dmitriy Serdyuk, Otavio Braga, Olivier Siohan

Proceedings of the Interspeech 2022, 2022

End-to-End multi-talker audio-visual ASR using an active speaker attention module.

Richard Rose, Olivier Siohan

Proceedings of the Interspeech 2022, 2022

Best of Both Worlds: Multi-Task Audio-Visual Automatic Speech Recognition and Active Speaker Detection.

Otavio Braga, Olivier Siohan

Proceedings of the IEEE International Conference on Acoustics, 2022

2021

Audio-Visual Speech Recognition is Worth 32×32×8 Voxels.

Dmitriy Serdyuk, Otavio Braga, Olivier Siohan

CoRR, 2021

Bridging the gap between streaming and non-streaming ASR systems bydistilling ensembles of CTC and RNN-T models.

Thibault Doutre, Wei Han, Chung-Cheng Chiu, Ruoming Pang, Olivier Siohan, Liangliang Cao

CoRR, 2021

End-to-End Audio-Visual Speech Recognition for Overlapping Speech.

Richard Rose, Olivier Siohan, Anshuman Tripathi, Otavio Braga

Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

Bridging the Gap Between Streaming and Non-Streaming ASR Systems by Distilling Ensembles of CTC and RNN-T Models.

Thibault Doutre, Wei Han, Chung-Cheng Chiu, Ruoming Pang, Olivier Siohan, Liangliang Cao

Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

A Closer Look at Audio-Visual Multi-Person Speech Recognition and Active Speaker Selection.

Otavio Braga, Olivier Siohan

Proceedings of the IEEE International Conference on Acoustics, 2021

Audio-Visual Speech Recognition is Worth $32\times 32\times 8$ Voxels.

Dmitriy Serdyuk, Otavio Braga, Olivier Siohan

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2021

Action Item Detection in Meetings Using Pretrained Transformers.

Kishan Sachdeva, Joshua Maynez, Olivier Siohan

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2021

2020

End-to-End Multi-Person Audio/Visual Automatic Speech Recognition.

Otavio Braga, Takaki Makino, Olivier Siohan, Hank Liao

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019

Recurrent Neural Network Transducer for Audio-Visual Speech Recognition.

Takaki Makino, Hank Liao, Yannis M. Assael, Brendan Shillingford, Basilio Garcia, Otavio Braga, Olivier Siohan

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2019

2017

CTC Training of Multi-Phone Acoustic Models for Speech Recognition.

Olivier Siohan

Proceedings of the Interspeech 2017, 2017

Annealed f-Smoothing as a Mechanism to Speed up Neural Network Training.

Tara N. Sainath, Vijayaditya Peddinti, Olivier Siohan, Arun Narayanan

Proceedings of the Interspeech 2017, 2017

Acoustic Modeling for Google Home.

Bo Li, Tara N. Sainath, Arun Narayanan, Joe Caroselli, Michiel Bacchiani, Ananya Misra, Izhak Shafran, Hasim Sak, Golan Pundak, Kean K. Chin, Khe Chai Sim, Ron J. Weiss, Kevin W. Wilson, Ehsan Variani, Chanwoo Kim, Olivier Siohan, Mitchel Weintraub, Erik McDermott, Richard Rose, Matt Shannon

Proceedings of the Interspeech 2017, 2017

2016

Automatic optimization of data perturbation distributions for multi-style training in speech recognition.

Mortaza Doulaty, Richard Rose, Olivier Siohan

Proceedings of the 2016 IEEE Spoken Language Technology Workshop, 2016

Selection and combination of hypotheses for dialectal speech recognition.

Victor Soto, Olivier Siohan, Mohamed Elfeky, Pedro J. Moreno

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Sequence training of multi-task acoustic models using meta-state labels.

Olivier Siohan

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

2015

Large vocabulary automatic speech recognition for children.

Hank Liao, Golan Pundak, Olivier Siohan, Melissa K. Carroll, Noah Coccaro, Qi-Ming Jiang, Tara N. Sainath, Andrew W. Senior, Françoise Beaufays, Michiel Bacchiani

Proceedings of the INTERSPEECH 2015, 2015

Exemplar-based large vocabulary speech recognition using k-nearest neighbors.

Yanbo Xu, Olivier Siohan, David Simcha, Sanjiv Kumar, Hank Liao

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

Multitask learning and system combination for automatic speech recognition.

Olivier Siohan, David Rybach

Proceedings of the 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, 2015

2014

A big data approach to acoustic model training corpus selection.

Olga Kapralova, John Alex, Eugene Weinstein, Pedro J. Moreno, Olivier Siohan

Proceedings of the INTERSPEECH 2014, 2014

Training data selection based on context-dependent state matching.

Olivier Siohan

Proceedings of the IEEE International Conference on Acoustics, 2014

2013

ivector-based acoustic data selection.

Olivier Siohan, Michiel Bacchiani

Proceedings of the INTERSPEECH 2013, 2013

2010

Decision tree state clustering with word and syllable features.

Hank Liao, Christopher Alberti, Michiel Bacchiani, Olivier Siohan

Proceedings of the INTERSPEECH 2010, 2010

2009

An audio indexing system for election video material.

Christopher Alberti, Michiel Bacchiani, Ari Bezman, Ciprian Chelba, Anastassia Drofa, Hank Liao, Pedro J. Moreno, Ted Power, Arnaud Sahuguet, Maria Shugrina, Olivier Siohan

Proceedings of the IEEE International Conference on Acoustics, 2009

2007

Comments on Vocal Tract Length Normalization Equals Linear Transformation in Cepstral Space.

Mohamed Afify, Olivier Siohan

IEEE Trans. Speech Audio Process., 2007

Vocabulary independent spoken term detection.

Jonathan Mamou, Bhuvana Ramabhadran, Olivier Siohan

Proceedings of the SIGIR 2007: Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2007

Gaussian Mixture Language Models for Speech Recognition.

Mohamed Afify, Olivier Siohan, Ruhi Sarikaya

Proceedings of the IEEE International Conference on Acoustics, 2007

The IBM 2007 speech transcription system for European parliamentary speeches.

Bhuvana Ramabhadran, Olivier Siohan, Abhinav Sethy

Proceedings of the IEEE Workshop on Automatic Speech Recognition & Understanding, 2007

2006

Automated Quality Monitoring for Call Centers using Speech and NLP Technologies.

Geoffrey Zweig, Olivier Siohan, George Saon, Bhuvana Ramabhadran, Daniel Povey, Lidia Mangu, Brian Kingsbury

Proceedings of the Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, 2006

The IBM Rich Transcription Spring 2006 Speech-to-Text System for Lecture Meetings.

Jing Huang, Martin Westphal, Stanley F. Chen, Olivier Siohan, Daniel Povey, Vit Libal, Alvaro Soneiro, Henrik Schulz, Thomas Ross, Gerasimos Potamianos

Proceedings of the Machine Learning for Multimodal Interaction, 2006

The IBM 2006 speech transcription system for european parliamentary speeches.

Bhuvana Ramabhadran, Olivier Siohan, Lidia Mangu, Geoffrey Zweig, Martin Westphal, Henrik Schulz, Alvaro Soneiro

Proceedings of the INTERSPEECH 2006, 2006

Automated Quality Monitoring in the Call Center with ASR and Maximum Entropy.

Geoffrey Zweig, Olivier Siohan, George Saon, Bhuvana Ramabhadran, Daniel Povey, Lidia Mangu, Brian Kingsbury

Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006

2005

A new verification-based fast-match for large vocabulary continuous speech recognition.

Mohamed Afify, Feng Liu, Hui Jiang, Olivier Siohan

IEEE Trans. Speech Audio Process., 2005

Fast vocabulary-independent audio search using path-based graph indexing.

Olivier Siohan, Michiel Bacchiani

Proceedings of the INTERSPEECH 2005, 2005

Contructing Ensembles of ASR Systems Using Randomized Decision Trees.

Olivier Siohan, Bhuvana Ramabhadran, Brian Kingsbury

Proceedings of the 2005 IEEE International Conference on Acoustics, 2005

2004

Sequential estimation with optimal forgetting for robust speech recognition.

Mohamed Afify, Olivier Siohan

IEEE Trans. Speech Audio Process., 2004

Speech recognition error analysis on the English MALACH corpus.

Olivier Siohan, Bhuvana Ramabhadran, Geoffrey Zweig

Proceedings of the INTERSPEECH 2004, 2004

Use of metadata to improve recognition of spontaneous speech and named entities.

Bhuvana Ramabhadran, Olivier Siohan, Geoffrey Zweig

Proceedings of the INTERSPEECH 2004, 2004

2003

Advances in natural language call routing.

Hong-Kwang Jeff Kuo, Olivier Siohan, Joseph P. Olive

Bell Labs Tech. J., 2003

Hierarchical class n-gram language models: towards better estimation of unseen events in speech recognition.

Imed Zitouni, Olivier Siohan, Chin-Hui Lee

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

Combining neighboring filter channels to improve quantile based histogram equalization.

Florian Hilger, Hermann Ney, Olivier Siohan, Frank K. Soong

Proceedings of the 2003 IEEE International Conference on Acoustics, 2003

2002

Upper and lower bounds on the mean of noisy speech: application to minimax classification.

Mohamed Afify, Olivier Siohan, Chin-Hui Lee

IEEE Trans. Speech Audio Process., 2002

Structural maximum a posteriori linear regression for fast HMM adaptation.

Olivier Siohan, Tor André Myrvoll, Chin-Hui Lee

Comput. Speech Lang., 2002

Backoff hierarchical class n-gram language modelling for automatic speech recognition systems.

Imed Zitouni, Olivier Siohan, Hong-Kwang Jeff Kuo, Chin-Hui Lee

Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

Bell labs approach to Aurora evaluation on connected digit recognition.

Jingdong Chen, Dimitris Dimitriadis, Hui Jiang, Qi Li, Tor André Myrvoll, Olivier Siohan, Frank K. Soong

Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

Towards knowledge-based features for HMM based large vocabulary automatic speech recognition.

Benoit Launay, Olivier Siohan, Arun C. Surendran, Chin-Hui Lee

Proceedings of the IEEE International Conference on Acoustics, 2002

A dynamic in-search discriminative training approach for large vocabulary speech recognition.

Hui Jiang, Olivier Siohan, Frank K. Soong, Chin-Hui Lee

Proceedings of the IEEE International Conference on Acoustics, 2002

A discriminative training criterion and an associated EM learning algorithm.

Mohamed Afify, Olivier Siohan

Proceedings of the IEEE International Conference on Acoustics, 2002

2001

Joint maximum a posteriori adaptation of transformation and HMM parameters.

Olivier Siohan, Cristina Chesta, Chin-Hui Lee

IEEE Trans. Speech Audio Process., 2001

A real-time Japanese broadcast news closed-captioning system.

Olivier Siohan, Akio Ando, Mohamed Afify, Hui Jiang, Chin-Hui Lee, Qi Li, Feng Liu, Kazuo Onoe, Frank K. Soong, Qiru Zhou

Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

A new verification-based fast match approach to large vocabulary speech recognition.

Feng Liu, Mohamed Afify, Hui Jiang, Olivier Siohan

Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

An auditory system-based feature for robust speech recognition.

Qi Li, Frank K. Soong, Olivier Siohan

Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

Minimax classification with parametric neighborhoods for noisy speech recognition.

Mohamed Afify, Olivier Siohan, Chin-Hui Lee

Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

Evaluating the Aurora connected digit recognition task - a bell labs approach.

Mohamed Afify, Hui Jiang, Filipp Korkmazskiy, Chin-Hui Lee, Qi Li, Olivier Siohan, Frank K. Soong, Arun C. Surendran

Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

Sequential noise estimation with optimal forgetting for robust speech recognition.

Mohamed Afify, Olivier Siohan

Proceedings of the IEEE International Conference on Acoustics, 2001

2000

Small group speaker identification with common password phrases.

Aaron E. Rosenberg, Olivier Siohan, Sarangarajan Parthasarathy

Speech Commun., 2000

Structural maximum a-posteriori linear regression for unsupervised speaker adaptation.

Tor André Myrvoll, Olivier Siohan, Chin-Hui Lee, Wu Chou

Proceedings of the Sixth International Conference on Spoken Language Processing, 2000

A high-performance auditory feature for robust speech recognition.

Qi Li, Frank K. Soong, Olivier Siohan

Proceedings of the Sixth International Conference on Spoken Language Processing, 2000

Extended maximum a posterior linear regression (EMAPLR) model adaptation for speech recognition.

Wu Chou, Olivier Siohan, Tor André Myrvoll, Chin-Hui Lee

Proceedings of the Sixth International Conference on Spoken Language Processing, 2000

Constrained maximum likelihood linear regression for speaker adaptation.

Mohamed Afify, Olivier Siohan

Proceedings of the Sixth International Conference on Spoken Language Processing, 2000

Joint maximum a posteriori estimation of transformation and hidden Markov model parameters.

Olivier Siohan, Cristina Chesta, Chin-Hui Lee

Proceedings of the IEEE International Conference on Acoustics, 2000

Multiple classifiers by constrained minimization.

Partha Niyogi, Jean-Benoît Pierrot, Olivier Siohan

Proceedings of the IEEE International Conference on Acoustics, 2000

1999

Maximum a posteriori linear regression for hidden Markov model adaptation.

Cristina Chesta, Olivier Siohan, Chin-Hui Lee

Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

Background model design for flexible and portable speaker verification systems.

Olivier Siohan, Chin-Hui Lee, Arun C. Surendran, Qi Li

Proceedings of the 1999 IEEE International Conference on Acoustics, 1999

1998

Speaker identification using minimum classification error training.

Olivier Siohan, Aaron E. Rosenberg, Sarangarajan Parthasarathy

Proceedings of the 1998 IEEE International Conference on Acoustics, 1998

Speaker verification using minimum verification error training.

Aaron E. Rosenberg, Olivier Siohan, Sarangarajan Parthasarathy

Proceedings of the 1998 IEEE International Conference on Acoustics, 1998

1997

Iterative noise and channel estimation under the stochastic matching algorithm framework.

Olivier Siohan, Chin-Hui Lee

IEEE Signal Process. Lett., 1997

1996

Comparative experiments of several adaptation approaches to noisy speech recognition using stochastic trajectory models.

Olivier Siohan, Yifan Gong, Jean Paul Haton

Speech Commun., 1996

A semi-continuous stochastic trajectory model for phoneme-based continuous speech recognition.

Olivier Siohan, Yifan Gong

Proceedings of the 1996 IEEE International Conference on Acoustics, 1996

1995

Reconnaissance automatique de la parole continue en environnement bruité : application à des modèles stochastiques de trajectoires. (Continuous speech recognition in a noisy environment : application to stochastic trajectory models).

Olivier Siohan

PhD thesis, 1995

Noise adaptation using linear regression for continuous noisy speech recognition.

Olivier Siohan, Yifan Gong, Jean Paul Haton

Proceedings of the Fourth European Conference on Speech Communication and Technology, 1995

On the robustness of linear discriminant analysis as a preprocessing step for noisy speech recognition.

Olivier Siohan

Proceedings of the 1995 International Conference on Acoustics, 1995

1994

A comparison of three noisy speech recognition approaches.

Olivier Siohan, Yifan Gong, Jean Paul Haton

Proceedings of the 3rd International Conference on Spoken Language Processing, 1994

1993

A Bayesian approach to phone duration adaptation for lombard speech recognition.

Olivier Siohan, Yifan Gong, Jean Paul Haton

Proceedings of the Third European Conference on Speech Communication and Technology, 1993

1992

Minimization of speech alignment error by iterative transformation for speaker adaptation.

Yifan Gong, Olivier Siohan, Jean Paul Haton

Proceedings of the Second International Conference on Spoken Language Processing, 1992