Olivier Siohan

Publication Activity (10 Years)

Years Active: 1992-2024
Publications (10 Years): 34

Top Venues

CoRR

ICASSP

INTERSPEECH

ASRU

Henri Poincaré University, Nancy, France (PHD)

Education History

Henri Poincaré University, Nancy, France

PHD

Publications

Oscar Chang, Hank Liao, Dmitriy Serdyuk, Ankit Shahy, Olivier Siohan
Conformer is All You Need for Visual Speech Recognition. ICASSP (2024)
Otavio Braga, Wei Xia, Keith Johnson, Alice Chuang, Yunfan Ye, Olivier Siohan, Tuan Anh Nguyen
Large Scale Self-Supervised Pretraining for Active Speaker Detection. ICASSP (2024)
Richard Rose, Oscar Chang, Olivier Siohan
Cascaded encoders for fine-tuning ASR models on overlapped speech. CoRR (2023)
Oscar Chang, Dongseong Hwang, Olivier Siohan
Revisiting the Entropy Semiring for Neural Speech Recognition. ICLR (2023)
Avner May, Dmitriy Serdyuk, Ankit Parag Shah, Otavio Braga, Olivier Siohan
Audio-visual fine-tuning of audio-only ASR models. CoRR (2023)
Oscar Chang, Hank Liao, Dmitriy Serdyuk, Ankit Shah, Olivier Siohan
Conformers are All You Need for Visual Speech Recogntion. CoRR (2023)
Oscar Chang, Otavio Braga, Hank Liao, Dmitriy Serdyuk, Olivier Siohan
On Robustness to Missing Video for Audiovisual Speech Recognition. CoRR (2023)
Oscar Chang, Dongseong Hwang, Olivier Siohan
Revisiting the Entropy Semiring for Neural Speech Recognition. CoRR (2023)
Richard Rose, Oscar Chang, Olivier Siohan
Cascaded encoders for fine-tuning ASR models on overlapped speech. INTERSPEECH (2023)
Oscar Chang, Otavio Braga, Hank Liao, Dmitriy Serdyuk, Olivier Siohan
On Robustness to Missing Video for Audiovisual Speech Recognition. Trans. Mach. Learn. Res. 2022 (2022)
Otavio Braga, Olivier Siohan
A Closer Look at Audio-Visual Multi-Person Speech Recognition and Active Speaker Selection. CoRR (2022)
Otavio Braga, Olivier Siohan
Best of Both Worlds: Multi-task Audio-Visual Automatic Speech Recognition and Active Speaker Detection. CoRR (2022)
Richard Rose, Olivier Siohan
End-to-end multi-talker audio-visual ASR using an active speaker attention module. CoRR (2022)
Dmitriy Serdyuk, Otavio Braga, Olivier Siohan
Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition for Single and Muti-Person Video. INTERSPEECH (2022)
Otavio Braga, Olivier Siohan
Best of Both Worlds: Multi-Task Audio-Visual Automatic Speech Recognition and Active Speaker Detection. ICASSP (2022)
Dmitriy Serdyuk, Otavio Braga, Olivier Siohan
Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition. CoRR (2022)
Richard Rose, Olivier Siohan
End-to-End multi-talker audio-visual ASR using an active speaker attention module. INTERSPEECH (2022)
Otavio Braga, Takaki Makino, Olivier Siohan, Hank Liao
End-to-End Multi-Person Audio/Visual Automatic Speech Recognition. CoRR (2022)
Thibault Doutre, Wei Han, Chung-Cheng Chiu, Ruoming Pang, Olivier Siohan, Liangliang Cao
Bridging the gap between streaming and non-streaming ASR systems bydistilling ensembles of CTC and RNN-T models. CoRR (2021)
Richard Rose, Olivier Siohan, Anshuman Tripathi, Otavio Braga
End-to-End Audio-Visual Speech Recognition for Overlapping Speech. Interspeech (2021)
Dmitriy Serdyuk, Otavio Braga, Olivier Siohan
Audio-Visual Speech Recognition is Worth 32×32×8 Voxels. CoRR (2021)
Otavio Braga, Olivier Siohan
A Closer Look at Audio-Visual Multi-Person Speech Recognition and Active Speaker Selection. ICASSP (2021)
Kishan Sachdeva, Joshua Maynez, Olivier Siohan
Action Item Detection in Meetings Using Pretrained Transformers. ASRU (2021)
Thibault Doutre, Wei Han, Chung-Cheng Chiu, Ruoming Pang, Olivier Siohan, Liangliang Cao
Bridging the Gap Between Streaming and Non-Streaming ASR Systems by Distilling Ensembles of CTC and RNN-T Models. Interspeech (2021)
Dmitriy Serdyuk, Otavio Braga, Olivier Siohan
Audio-Visual Speech Recognition is Worth $32\times 32\times 8$ Voxels. ASRU (2021)
Otavio Braga, Takaki Makino, Olivier Siohan, Hank Liao
End-to-End Multi-Person Audio/Visual Automatic Speech Recognition. ICASSP (2020)
Takaki Makino, Hank Liao, Yannis M. Assael, Brendan Shillingford, Basilio Garcia, Otavio Braga, Olivier Siohan
Recurrent Neural Network Transducer for Audio-Visual Speech Recognition. CoRR (2019)
Takaki Makino, Hank Liao, Yannis M. Assael, Brendan Shillingford, Basilio Garcia, Otavio Braga, Olivier Siohan
Recurrent Neural Network Transducer for Audio-Visual Speech Recognition. ASRU (2019)
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
Acoustic Modeling for Google Home. INTERSPEECH (2017)
Olivier Siohan
CTC Training of Multi-Phone Acoustic Models for Speech Recognition. INTERSPEECH (2017)
Tara N. Sainath, Vijayaditya Peddinti, Olivier Siohan, Arun Narayanan
Annealed f-Smoothing as a Mechanism to Speed up Neural Network Training. INTERSPEECH (2017)
Victor Soto, Olivier Siohan, Mohamed Elfeky, Pedro J. Moreno
Selection and combination of hypotheses for dialectal speech recognition. ICASSP (2016)
Mortaza Doulaty, Richard Rose, Olivier Siohan
Automatic optimization of data perturbation distributions for multi-style training in speech recognition. SLT (2016)
Olivier Siohan
Sequence training of multi-task acoustic models using meta-state labels. ICASSP (2016)
Hank Liao, Golan Pundak, Olivier Siohan, Melissa K. Carroll, Noah Coccaro, Qi-Ming Jiang, Tara N. Sainath, Andrew W. Senior, Françoise Beaufays, Michiel Bacchiani
Large vocabulary automatic speech recognition for children. INTERSPEECH (2015)
Yanbo Xu, Olivier Siohan, David Simcha, Sanjiv Kumar, Hank Liao
Exemplar-based large vocabulary speech recognition using k-nearest neighbors. ICASSP (2015)
Olivier Siohan, David Rybach
Multitask learning and system combination for automatic speech recognition. ASRU (2015)
Olga Kapralova, John Alex, Eugene Weinstein, Pedro J. Moreno, Olivier Siohan
A big data approach to acoustic model training corpus selection. INTERSPEECH (2014)
Olivier Siohan
Training data selection based on context-dependent state matching. ICASSP (2014)
Olivier Siohan, Michiel Bacchiani
ivector-based acoustic data selection. INTERSPEECH (2013)
Hank Liao, Christopher Alberti, Michiel Bacchiani, Olivier Siohan
Decision tree state clustering with word and syllable features. INTERSPEECH (2010)
Christopher Alberti, Michiel Bacchiani, Ari Bezman, Ciprian Chelba, Anastassia Drofa, Hank Liao, Pedro J. Moreno, Ted Power, Arnaud Sahuguet, Maria Shugrina, Olivier Siohan
An audio indexing system for election video material. ICASSP (2009)
Bhuvana Ramabhadran, Olivier Siohan, Abhinav Sethy
The IBM 2007 speech transcription system for European parliamentary speeches. ASRU (2007)
Mohamed Afify, Olivier Siohan
Comments on Vocal Tract Length Normalization Equals Linear Transformation in Cepstral Space. IEEE Trans. Speech Audio Process. 15 (5) (2007)
Jonathan Mamou, Bhuvana Ramabhadran, Olivier Siohan
Vocabulary independent spoken term detection. SIGIR (2007)
Mohamed Afify, Olivier Siohan, Ruhi Sarikaya
Gaussian Mixture Language Models for Speech Recognition. ICASSP (4) (2007)
Geoffrey Zweig, Olivier Siohan, George Saon, Bhuvana Ramabhadran, Daniel Povey, Lidia Mangu, Brian Kingsbury
Automated Quality Monitoring in the Call Center with ASR and Maximum Entropy. ICASSP (1) (2006)
Geoffrey Zweig, Olivier Siohan, George Saon, Bhuvana Ramabhadran, Daniel Povey, Lidia Mangu, Brian Kingsbury
Automated Quality Monitoring for Call Centers using Speech and NLP Technologies. HLT-NAACL (2006)
Jing Huang, Martin Westphal, Stanley F. Chen, Olivier Siohan, Daniel Povey, Vit Libal, Alvaro Soneiro, Henrik Schulz, Thomas Ross, Gerasimos Potamianos
The IBM Rich Transcription Spring 2006 Speech-to-Text System for Lecture Meetings. MLMI (2006)
Bhuvana Ramabhadran, Olivier Siohan, Lidia Mangu, Geoffrey Zweig, Martin Westphal, Henrik Schulz, Alvaro Soneiro
The IBM 2006 speech transcription system for european parliamentary speeches. INTERSPEECH (2006)
Olivier Siohan, Bhuvana Ramabhadran, Brian Kingsbury
Contructing Ensembles of ASR Systems Using Randomized Decision Trees. ICASSP (1) (2005)
Olivier Siohan, Michiel Bacchiani
Fast vocabulary-independent audio search using path-based graph indexing. INTERSPEECH (2005)
Mohamed Afify, Feng Liu, Hui Jiang, Olivier Siohan
A new verification-based fast-match for large vocabulary continuous speech recognition. IEEE Trans. Speech Audio Process. 13 (4) (2005)
Olivier Siohan, Bhuvana Ramabhadran, Geoffrey Zweig
Speech recognition error analysis on the English MALACH corpus. INTERSPEECH (2004)
Bhuvana Ramabhadran, Olivier Siohan, Geoffrey Zweig
Use of metadata to improve recognition of spontaneous speech and named entities. INTERSPEECH (2004)
Mohamed Afify, Olivier Siohan
Sequential estimation with optimal forgetting for robust speech recognition. IEEE Trans. Speech Audio Process. 12 (1) (2004)
Florian Hilger, Hermann Ney, Olivier Siohan, Frank K. Soong
Combining neighboring filter channels to improve quantile based histogram equalization. ICASSP (1) (2003)
Imed Zitouni, Olivier Siohan, Chin-Hui Lee
Hierarchical class n-gram language models: towards better estimation of unseen events in speech recognition. INTERSPEECH (2003)
Hong-Kwang Jeff Kuo, Olivier Siohan, Joseph P. Olive
Advances in natural language call routing. Bell Labs Tech. J. 7 (3) (2003)
Benoit Launay, Olivier Siohan, Arun C. Surendran, Chin-Hui Lee
Towards knowledge-based features for HMM based large vocabulary automatic speech recognition. ICASSP (2002)
Hui Jiang, Olivier Siohan, Frank K. Soong, Chin-Hui Lee
A dynamic in-search discriminative training approach for large vocabulary speech recognition. ICASSP (2002)
Mohamed Afify, Olivier Siohan, Chin-Hui Lee
Upper and lower bounds on the mean of noisy speech: application to minimax classification. IEEE Trans. Speech Audio Process. 10 (2) (2002)
Imed Zitouni, Olivier Siohan, Hong-Kwang Jeff Kuo, Chin-Hui Lee
Backoff hierarchical class n-gram language modelling for automatic speech recognition systems. INTERSPEECH (2002)
Jingdong Chen, Dimitris Dimitriadis, Hui Jiang, Qi Li, Tor André Myrvoll, Olivier Siohan, Frank K. Soong
Bell labs approach to Aurora evaluation on connected digit recognition. INTERSPEECH (2002)
Olivier Siohan, Tor André Myrvoll, Chin-Hui Lee
Structural maximum a posteriori linear regression for fast HMM adaptation. Comput. Speech Lang. 16 (1) (2002)
Mohamed Afify, Olivier Siohan
A discriminative training criterion and an associated EM learning algorithm. ICASSP (2002)
Feng Liu, Mohamed Afify, Hui Jiang, Olivier Siohan
A new verification-based fast match approach to large vocabulary speech recognition. INTERSPEECH (2001)
Olivier Siohan, Cristina Chesta, Chin-Hui Lee
Joint maximum a posteriori adaptation of transformation and HMM parameters. IEEE Trans. Speech Audio Process. 9 (4) (2001)
Mohamed Afify, Olivier Siohan, Chin-Hui Lee
Minimax classification with parametric neighborhoods for noisy speech recognition. INTERSPEECH (2001)
Mohamed Afify, Hui Jiang, Filipp Korkmazskiy, Chin-Hui Lee, Qi Li, Olivier Siohan, Frank K. Soong, Arun C. Surendran
Evaluating the Aurora connected digit recognition task - a bell labs approach. INTERSPEECH (2001)
Mohamed Afify, Olivier Siohan
Sequential noise estimation with optimal forgetting for robust speech recognition. ICASSP (2001)
Olivier Siohan, Akio Ando, Mohamed Afify, Hui Jiang, Chin-Hui Lee, Qi Li, Feng Liu, Kazuo Onoe, Frank K. Soong, Qiru Zhou
A real-time Japanese broadcast news closed-captioning system. INTERSPEECH (2001)
Qi Li, Frank K. Soong, Olivier Siohan
An auditory system-based feature for robust speech recognition. INTERSPEECH (2001)
Mohamed Afify, Olivier Siohan
Constrained maximum likelihood linear regression for speaker adaptation. INTERSPEECH (2000)
Wu Chou, Olivier Siohan, Tor André Myrvoll, Chin-Hui Lee
Extended maximum a posterior linear regression (EMAPLR) model adaptation for speech recognition. INTERSPEECH (2000)
Olivier Siohan, Cristina Chesta, Chin-Hui Lee
Joint maximum a posteriori estimation of transformation and hidden Markov model parameters. ICASSP (2000)
Qi Li, Frank K. Soong, Olivier Siohan
A high-performance auditory feature for robust speech recognition. INTERSPEECH (2000)
Aaron E. Rosenberg, Olivier Siohan, Sarangarajan Parthasarathy
Small group speaker identification with common password phrases. Speech Commun. 31 (2-3) (2000)
Tor André Myrvoll, Olivier Siohan, Chin-Hui Lee, Wu Chou
Structural maximum a-posteriori linear regression for unsupervised speaker adaptation. INTERSPEECH (2000)
Partha Niyogi, Jean-Benoit Pierrot, Olivier Siohan
Multiple classifiers by constrained minimization. ICASSP (2000)
Cristina Chesta, Olivier Siohan, Chin-Hui Lee
Maximum a posteriori linear regression for hidden Markov model adaptation. EUROSPEECH (1999)
Olivier Siohan, Chin-Hui Lee, Arun C. Surendran, Qi Li
Background model design for flexible and portable speaker verification systems. ICASSP (1999)
Aaron E. Rosenberg, Olivier Siohan, Sarangarajan Parthasarathy
Speaker verification using minimum verification error training. ICASSP (1998)
Olivier Siohan, Aaron E. Rosenberg, Sarangarajan Parthasarathy
Speaker identification using minimum classification error training. ICASSP (1998)
Olivier Siohan, Chin-Hui Lee
Iterative noise and channel estimation under the stochastic matching algorithm framework. IEEE Signal Process. Lett. 4 (11) (1997)
Olivier Siohan, Yifan Gong, Jean Paul Haton
Comparative experiments of several adaptation approaches to noisy speech recognition using stochastic trajectory models. Speech Commun. 18 (4) (1996)
Olivier Siohan, Yifan Gong
A semi-continuous stochastic trajectory model for phoneme-based continuous speech recognition. ICASSP (1996)
Olivier Siohan, Yifan Gong, Jean Paul Haton
Noise adaptation using linear regression for continuous noisy speech recognition. EUROSPEECH (1995)
Olivier Siohan
On the robustness of linear discriminant analysis as a preprocessing step for noisy speech recognition. ICASSP (1995)
Olivier Siohan, Yifan Gong, Jean Paul Haton
A comparison of three noisy speech recognition approaches. ICSLP (1994)
Olivier Siohan, Yifan Gong, Jean Paul Haton
A Bayesian approach to phone duration adaptation for lombard speech recognition. EUROSPEECH (1993)
Yifan Gong, Olivier Siohan, Jean Paul Haton
Minimization of speech alignment error by iterative transformation for speaker adaptation. ICSLP (1992)

Olivier Siohan.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Olivier Siohan