Olivier Siohan

94 papers A* 2A 28C 5Misc 21Journal 25Unranked 12

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Multi-Channel Differential ASR for Robust Wearer Speech Recognition on Smart Glasses. CoRR Yufeng Yang, Yiteng Huang, Yong Xu, Li Wan, Suwon Shon, Yang Liu, Yifeng Fan, Zhaojun Yang, Olivier Siohan, Yue Liu, Ming Sun, Florian Metze
2024	Misc	`conf`	Conformer is All You Need for Visual Speech Recognition. ICASSP Oscar Chang, Hank Liao, Dmitriy Serdyuk, Ankit Shahy, Olivier Siohan
2024	Misc	`conf`	Large Scale Self-Supervised Pretraining for Active Speaker Detection. ICASSP Otavio Braga, Wei Xia, Keith Johnson, Alice Chuang, Yunfan Ye, Olivier Siohan, Tuan Anh Nguyen
2023	J	`jnl`	Audio-visual fine-tuning of audio-only ASR models. CoRR Avner May, Dmitriy Serdyuk, Ankit Parag Shah, Otavio Braga, Olivier Siohan
2023	A	`conf`	Cascaded encoders for fine-tuning ASR models on overlapped speech. INTERSPEECH Richard Rose, Oscar Chang, Olivier Siohan
2023	J	`jnl`	Cascaded encoders for fine-tuning ASR models on overlapped speech. CoRR Richard Rose, Oscar Chang, Olivier Siohan
2023	J	`jnl`	Conformers are All You Need for Visual Speech Recogntion. CoRR Oscar Chang, Hank Liao, Dmitriy Serdyuk, Ankit Parag Shah, Olivier Siohan
2023	J	`jnl`	On Robustness to Missing Video for Audiovisual Speech Recognition. CoRR Oscar Chang, Otavio Braga, Hank Liao, Dmitriy Serdyuk, Olivier Siohan
2023	A*	`conf`	Revisiting the Entropy Semiring for Neural Speech Recognition. ICLR Oscar Chang, Dongseong Hwang, Olivier Siohan
2023	J	`jnl`	Revisiting the Entropy Semiring for Neural Speech Recognition. CoRR Oscar Chang, Dongseong Hwang, Olivier Siohan
2022	J	`jnl`	A Closer Look at Audio-Visual Multi-Person Speech Recognition and Active Speaker Selection. CoRR Otavio Braga, Olivier Siohan
2022	Misc	`conf`	Best of Both Worlds: Multi-Task Audio-Visual Automatic Speech Recognition and Active Speaker Detection. ICASSP Otavio Braga, Olivier Siohan
2022	J	`jnl`	Best of Both Worlds: Multi-task Audio-Visual Automatic Speech Recognition and Active Speaker Detection. CoRR Otavio Braga, Olivier Siohan
2022	J	`jnl`	End-to-End Multi-Person Audio/Visual Automatic Speech Recognition. CoRR Otavio Braga, Takaki Makino, Olivier Siohan, Hank Liao
2022	A	`conf`	End-to-End multi-talker audio-visual ASR using an active speaker attention module. INTERSPEECH Richard Rose, Olivier Siohan
2022	J	`jnl`	End-to-end multi-talker audio-visual ASR using an active speaker attention module. CoRR Richard Rose, Olivier Siohan
2022	J	`jnl`	On Robustness to Missing Video for Audiovisual Speech Recognition. Trans. Mach. Learn. Res. Oscar Chang, Otavio Braga, Hank Liao, Dmitriy Serdyuk, Olivier Siohan
2022	A	`conf`	Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition for Single and Muti-Person Video. INTERSPEECH Dmitriy Serdyuk, Otavio Braga, Olivier Siohan
2022	J	`jnl`	Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition. CoRR Dmitriy Serdyuk, Otavio Braga, Olivier Siohan
2021	Misc	`conf`	A Closer Look at Audio-Visual Multi-Person Speech Recognition and Active Speaker Selection. ICASSP Otavio Braga, Olivier Siohan
2021	C	`conf`	Action Item Detection in Meetings Using Pretrained Transformers. ASRU Kishan Sachdeva, Joshua Maynez, Olivier Siohan
2021	C	`conf`	Audio-Visual Speech Recognition is Worth $32\times 32\times 8$ Voxels. ASRU Dmitriy Serdyuk, Otavio Braga, Olivier Siohan
2021	J	`jnl`	Audio-Visual Speech Recognition is Worth 32×32×8 Voxels. CoRR Dmitriy Serdyuk, Otavio Braga, Olivier Siohan
2021	A	`conf`	Bridging the Gap Between Streaming and Non-Streaming ASR Systems by Distilling Ensembles of CTC and RNN-T Models. Interspeech Thibault Doutre, Wei Han, Chung-Cheng Chiu, Ruoming Pang, Olivier Siohan, Liangliang Cao
2021	J	`jnl`	Bridging the gap between streaming and non-streaming ASR systems bydistilling ensembles of CTC and RNN-T models. CoRR Thibault Doutre, Wei Han, Chung-Cheng Chiu, Ruoming Pang, Olivier Siohan, Liangliang Cao
2021	A	`conf`	End-to-End Audio-Visual Speech Recognition for Overlapping Speech. Interspeech Richard Rose, Olivier Siohan, Anshuman Tripathi, Otavio Braga
2020	Misc	`conf`	End-to-End Multi-Person Audio/Visual Automatic Speech Recognition. ICASSP Otavio Braga, Takaki Makino, Olivier Siohan, Hank Liao
2019	C	`conf`	Recurrent Neural Network Transducer for Audio-Visual Speech Recognition. ASRU Takaki Makino, Hank Liao, Yannis M. Assael, Brendan Shillingford, Basilio Garcia, Otavio Braga, Olivier Siohan
2019	J	`jnl`	Recurrent Neural Network Transducer for Audio-Visual Speech Recognition. CoRR Takaki Makino, Hank Liao, Yannis M. Assael, Brendan Shillingford, Basilio Garcia, Otavio Braga, Olivier Siohan
2017	A	`conf`	Acoustic Modeling for Google Home. INTERSPEECH 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
2017	A	`conf`	Annealed f-Smoothing as a Mechanism to Speed up Neural Network Training. INTERSPEECH Tara N. Sainath, Vijayaditya Peddinti, Olivier Siohan, Arun Narayanan
2017	A	`conf`	CTC Training of Multi-Phone Acoustic Models for Speech Recognition. INTERSPEECH Olivier Siohan
2016	—	`conf`	Automatic optimization of data perturbation distributions for multi-style training in speech recognition. SLT Mortaza Doulaty, Richard Rose, Olivier Siohan
2016	Misc	`conf`	Selection and combination of hypotheses for dialectal speech recognition. ICASSP Victor Soto, Olivier Siohan, Mohamed Elfeky, Pedro J. Moreno
2016	Misc	`conf`	Sequence training of multi-task acoustic models using meta-state labels. ICASSP Olivier Siohan
2015	Misc	`conf`	Exemplar-based large vocabulary speech recognition using k-nearest neighbors. ICASSP Yanbo Xu, Olivier Siohan, David Simcha, Sanjiv Kumar, Hank Liao
2015	A	`conf`	Large vocabulary automatic speech recognition for children. INTERSPEECH Hank Liao, Golan Pundak, Olivier Siohan, Melissa K. Carroll, Noah Coccaro, Qi-Ming Jiang, Tara N. Sainath, Andrew W. Senior, Françoise Beaufays, Michiel Bacchiani
2015	C	`conf`	Multitask learning and system combination for automatic speech recognition. ASRU Olivier Siohan, David Rybach
2014	A	`conf`	A big data approach to acoustic model training corpus selection. INTERSPEECH Olga Kapralova, John Alex, Eugene Weinstein, Pedro J. Moreno, Olivier Siohan
2014	Misc	`conf`	Training data selection based on context-dependent state matching. ICASSP Olivier Siohan
2013	A	`conf`	ivector-based acoustic data selection. INTERSPEECH Olivier Siohan, Michiel Bacchiani
2010	A	`conf`	Decision tree state clustering with word and syllable features. INTERSPEECH Hank Liao, Christopher Alberti, Michiel Bacchiani, Olivier Siohan
2009	Misc	`conf`	An audio indexing system for election video material. ICASSP Christopher Alberti, Michiel Bacchiani, Ari Bezman, Ciprian Chelba, Anastassia Drofa, Hank Liao, Pedro J. Moreno, Ted Power, Arnaud Sahuguet, Maria Shugrina, Olivier Siohan
2007	J	`jnl`	Comments on Vocal Tract Length Normalization Equals Linear Transformation in Cepstral Space. IEEE Trans. Speech Audio Process. Mohamed Afify, Olivier Siohan
2007	—	`conf`	Gaussian Mixture Language Models for Speech Recognition. ICASSP (4) Mohamed Afify, Olivier Siohan, Ruhi Sarikaya
2007	C	`conf`	The IBM 2007 speech transcription system for European parliamentary speeches. ASRU Bhuvana Ramabhadran, Olivier Siohan, Abhinav Sethy
2007	A*	`conf`	Vocabulary independent spoken term detection. SIGIR Jonathan Mamou, Bhuvana Ramabhadran, Olivier Siohan
2006	—	`conf`	Automated Quality Monitoring for Call Centers using Speech and NLP Technologies. HLT-NAACL Geoffrey Zweig, Olivier Siohan, George Saon, Bhuvana Ramabhadran, Daniel Povey, Lidia Mangu, Brian Kingsbury
2006	—	`conf`	Automated Quality Monitoring in the Call Center with ASR and Maximum Entropy. ICASSP (1) Geoffrey Zweig, Olivier Siohan, George Saon, Bhuvana Ramabhadran, Daniel Povey, Lidia Mangu, Brian Kingsbury
2006	A	`conf`	The IBM 2006 speech transcription system for european parliamentary speeches. INTERSPEECH Bhuvana Ramabhadran, Olivier Siohan, Lidia Mangu, Geoffrey Zweig, Martin Westphal, Henrik Schulz, Alvaro Soneiro
2006	—	`conf`	The IBM Rich Transcription Spring 2006 Speech-to-Text System for Lecture Meetings. MLMI Jing Huang, Martin Westphal, Stanley F. Chen, Olivier Siohan, Daniel Povey, Vit Libal, Alvaro Soneiro, Henrik Schulz, Thomas Ross, Gerasimos Potamianos
2005	J	`jnl`	A new verification-based fast-match for large vocabulary continuous speech recognition. IEEE Trans. Speech Audio Process. Mohamed Afify, Feng Liu, Hui Jiang, Olivier Siohan
2005	—	`conf`	Contructing Ensembles of ASR Systems Using Randomized Decision Trees. ICASSP (1) Olivier Siohan, Bhuvana Ramabhadran, Brian Kingsbury
2005	A	`conf`	Fast vocabulary-independent audio search using path-based graph indexing. INTERSPEECH Olivier Siohan, Michiel Bacchiani
2004	J	`jnl`	Sequential estimation with optimal forgetting for robust speech recognition. IEEE Trans. Speech Audio Process. Mohamed Afify, Olivier Siohan
2004	A	`conf`	Speech recognition error analysis on the English MALACH corpus. INTERSPEECH Olivier Siohan, Bhuvana Ramabhadran, Geoffrey Zweig
2004	A	`conf`	Use of metadata to improve recognition of spontaneous speech and named entities. INTERSPEECH Bhuvana Ramabhadran, Olivier Siohan, Geoffrey Zweig
2003	J	`jnl`	Advances in natural language call routing. Bell Labs Tech. J. Hong-Kwang Jeff Kuo, Olivier Siohan, Joseph P. Olive
2003	—	`conf`	Combining neighboring filter channels to improve quantile based histogram equalization. ICASSP (1) Florian Hilger, Hermann Ney, Olivier Siohan, Frank K. Soong
2003	A	`conf`	Hierarchical class n-gram language models: towards better estimation of unseen events in speech recognition. INTERSPEECH Imed Zitouni, Olivier Siohan, Chin-Hui Lee
2002	Misc	`conf`	A discriminative training criterion and an associated EM learning algorithm. ICASSP Mohamed Afify, Olivier Siohan
2002	Misc	`conf`	A dynamic in-search discriminative training approach for large vocabulary speech recognition. ICASSP Hui Jiang, Olivier Siohan, Frank K. Soong, Chin-Hui Lee
2002	A	`conf`	Backoff hierarchical class n-gram language modelling for automatic speech recognition systems. INTERSPEECH Imed Zitouni, Olivier Siohan, Hong-Kwang Jeff Kuo, Chin-Hui Lee
2002	A	`conf`	Bell labs approach to Aurora evaluation on connected digit recognition. INTERSPEECH Jingdong Chen, Dimitris Dimitriadis, Hui Jiang, Qi Li, Tor André Myrvoll, Olivier Siohan, Frank K. Soong
2002	J	`jnl`	Structural maximum a posteriori linear regression for fast HMM adaptation. Comput. Speech Lang. Olivier Siohan, Tor André Myrvoll, Chin-Hui Lee
2002	Misc	`conf`	Towards knowledge-based features for HMM based large vocabulary automatic speech recognition. ICASSP Benoit Launay, Olivier Siohan, Arun C. Surendran, Chin-Hui Lee
2002	J	`jnl`	Upper and lower bounds on the mean of noisy speech: application to minimax classification. IEEE Trans. Speech Audio Process. Mohamed Afify, Olivier Siohan, Chin-Hui Lee
2001	A	`conf`	A new verification-based fast match approach to large vocabulary speech recognition. INTERSPEECH Feng Liu, Mohamed Afify, Hui Jiang, Olivier Siohan
2001	A	`conf`	A real-time Japanese broadcast news closed-captioning system. INTERSPEECH Olivier Siohan, Akio Ando, Mohamed Afify, Hui Jiang, Chin-Hui Lee, Qi Li, Feng Liu, Kazuo Onoe, Frank K. Soong, Qiru Zhou
2001	A	`conf`	An auditory system-based feature for robust speech recognition. INTERSPEECH Qi Li, Frank K. Soong, Olivier Siohan
2001	A	`conf`	Evaluating the Aurora connected digit recognition task - a bell labs approach. INTERSPEECH Mohamed Afify, Hui Jiang, Filipp Korkmazskiy, Chin-Hui Lee, Qi Li, Olivier Siohan, Frank K. Soong, Arun C. Surendran
2001	J	`jnl`	Joint maximum a posteriori adaptation of transformation and HMM parameters. IEEE Trans. Speech Audio Process. Olivier Siohan, Cristina Chesta, Chin-Hui Lee
2001	A	`conf`	Minimax classification with parametric neighborhoods for noisy speech recognition. INTERSPEECH Mohamed Afify, Olivier Siohan, Chin-Hui Lee
2001	Misc	`conf`	Sequential noise estimation with optimal forgetting for robust speech recognition. ICASSP Mohamed Afify, Olivier Siohan
2000	A	`conf`	A high-performance auditory feature for robust speech recognition. INTERSPEECH Qi Li, Frank K. Soong, Olivier Siohan
2000	A	`conf`	Constrained maximum likelihood linear regression for speaker adaptation. INTERSPEECH Mohamed Afify, Olivier Siohan
2000	A	`conf`	Extended maximum a posterior linear regression (EMAPLR) model adaptation for speech recognition. INTERSPEECH Wu Chou, Olivier Siohan, Tor André Myrvoll, Chin-Hui Lee
2000	Misc	`conf`	Joint maximum a posteriori estimation of transformation and hidden Markov model parameters. ICASSP Olivier Siohan, Cristina Chesta, Chin-Hui Lee
2000	Misc	`conf`	Multiple classifiers by constrained minimization. ICASSP Partha Niyogi, Jean-Benoît Pierrot, Olivier Siohan
2000	J	`jnl`	Small group speaker identification with common password phrases. Speech Commun. Aaron E. Rosenberg, Olivier Siohan, Sarangarajan Parthasarathy
2000	A	`conf`	Structural maximum a-posteriori linear regression for unsupervised speaker adaptation. INTERSPEECH Tor André Myrvoll, Olivier Siohan, Chin-Hui Lee, Wu Chou
1999	Misc	`conf`	Background model design for flexible and portable speaker verification systems. ICASSP Olivier Siohan, Chin-Hui Lee, Arun C. Surendran, Qi Li
1999	—	`conf`	Maximum a posteriori linear regression for hidden Markov model adaptation. EUROSPEECH Cristina Chesta, Olivier Siohan, Chin-Hui Lee
1998	Misc	`conf`	Speaker identification using minimum classification error training. ICASSP Olivier Siohan, Aaron E. Rosenberg, Sarangarajan Parthasarathy
1998	Misc	`conf`	Speaker verification using minimum verification error training. ICASSP Aaron E. Rosenberg, Olivier Siohan, Sarangarajan Parthasarathy
1997	J	`jnl`	Iterative noise and channel estimation under the stochastic matching algorithm framework. IEEE Signal Process. Lett. Olivier Siohan, Chin-Hui Lee
1996	Misc	`conf`	A semi-continuous stochastic trajectory model for phoneme-based continuous speech recognition. ICASSP Olivier Siohan, Yifan Gong
1996	J	`jnl`	Comparative experiments of several adaptation approaches to noisy speech recognition using stochastic trajectory models. Speech Commun. Olivier Siohan, Yifan Gong, Jean Paul Haton
1995	—	`conf`	Noise adaptation using linear regression for continuous noisy speech recognition. EUROSPEECH Olivier Siohan, Yifan Gong, Jean Paul Haton
1995	Misc	`conf`	On the robustness of linear discriminant analysis as a preprocessing step for noisy speech recognition. ICASSP Olivier Siohan
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
1994	—	`conf`	A comparison of three noisy speech recognition approaches. ICSLP Olivier Siohan, Yifan Gong, Jean Paul Haton
1993	—	`conf`	A Bayesian approach to phone duration adaptation for lombard speech recognition. EUROSPEECH Olivier Siohan, Yifan Gong, Jean Paul Haton
1992	—	`conf`	Minimization of speech alignment error by iterative transformation for speaker adaptation. ICSLP Yifan Gong, Olivier Siohan, Jean Paul Haton