Man-Hung Siu

According to our database, Man-Hung Siu authored at least 93 papers between 1991 and 2023.

Collaborative distances:

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

2023

Personalization of CTC-based End-to-End Speech Recognition Using Pronunciation-Driven Subword Tokenization.

Zhihong Lei, Ernest Pusateri, Shiyi Han, Leo Liu, Mingbin Xu, Tim Ng, Ruchir Travadi, Youyuan Zhang, Mirko Hannemann, Man-Hung Siu, Zhen Huang

CoRR, 2023

Acoustic Model Fusion For End-to-End Speech Recognition.

Zhihong Lei, Mingbin Xu, Shiyi Han, Leo Liu, Zhen Huang, Tim Ng, Yuanyuan Zhang, Ernest Pusateri, Mirko Hannemann, Yaqiao Deng, Man-Hung Siu

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023

2020

Learning from Noisy Labels with Noise Modeling Network.

Zhuolin Jiang, Jan Silovský, Man-Hung Siu, William Hartmann, Herbert Gish, Sancar Adali

CoRR, 2020

Towards a New Understanding of the Training of Neural Networks with Mislabeled Training Data.

Herbert Gish, Jan Silovský, Man-Ling Sung, Man-Hung Siu, William Hartmann, Zhuolin Jiang

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2018

Optimizing Multilingual Knowledge Transfer for Time-Delay Neural Networks with Low-Rank Factorization.

Francis Keith, William Hartmann, Man-Hung Siu, Jeff Z. Ma, Owen Kimball

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017

Improving Deliverable Speech-to-Text Systems with Multilingual Knowledge Transfer.

Jeff Z. Ma, Francis Keith, Tim Ng, Man-Hung Siu, Owen Kimball

Proceedings of the Interspeech 2017, 2017

Improved Single System Conversational Telephone Speech Recognition with VGG Bottleneck Features.

William Hartmann, Roger Hsiao, Tim Ng, Jeff Z. Ma, Francis Keith, Man-Hung Siu

Proceedings of the Interspeech 2017, 2017

Unsupervised adaptation for deep neural networks using Alternating Direction Method of Multipliers.

Roger Hsiao, Tim Ng, Man-Hung Siu

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

2016

Sage: The New BBN Speech Processing Platform.

Roger Hsiao, Ralf Meermeier, Tim Ng, Zhongqiang Huang, Maxwell Jordan, Enoch Kan, Tanel Alumäe, Jan Silovský, William Hartmann, Francis Keith, Omer Lang, Man-Hung Siu, Owen Kimball

Proceedings of the Interspeech 2016, 2016

Importance sampling of delta-AUC: A basis for active learning for improved keyword search.

Kerri Barnes, Matthew Snover, Man-Hung Siu, Herbert Gish

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

2015

Large-scale speaker search using PLDA on mismatched conditions.

Jeff Z. Ma, Jan Silovský, Man-Hung Siu, Owen Kimball

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

2014

Unsupervised training of an HMM-based self-organizing unit recognizer with applications to topic classification and keyword discovery.

Man-Hung Siu, Herbert Gish, Arthur Chan, William Belfield, Steve Lowe

Comput. Speech Lang., 2014

2012

MLLR transforms of self-organized units as features in speaker recognition.

Man-Hung Siu, Omer Lang, Herbert Gish, Stephen A. Lowe, Arthur Chan, Owen Kimball

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

Detection of unseen words in conversational Mandarin.

Ivan Bulyko, Owen Kimball, Man-Hung Siu, Jose Herrero, Dan Blum

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

2011

Unsupervised Audio Patterns Discovery Using HMM-Based Self-Organized Units.

Man-Hung Siu, Herbert Gish, Steve Lowe, Arthur Chan

Proceedings of the INTERSPEECH 2011, 2011

Topic modeling for spoken documents using only phonetic information.

Timothy J. Hazen, Man-Hung Siu, Herbert Gish, Steve Lowe, Arthur Chan

Proceedings of the 2011 IEEE Workshop on Automatic Speech Recognition & Understanding, 2011

2010

Improved named entity extraction from conversational speech with language model adaptation.

Man-Hung Siu, Ted Vessenes, Ivan Bulyko, Owen Kimball

Proceedings of the 2010 IEEE Spoken Language Technology Workshop, 2010

Improved topic classification and keyword discovery using an HMM-based speech recognizer trained without supervision.

Man-Hung Siu, Herbert Gish, Arthur Chan, William Belfield

Proceedings of the INTERSPEECH 2010, 2010

2009

Discriminatively Trained GMMs for Language Classification Using Boosting Methods.

Man-Hung Siu, Xi Yang, Herbert Gish

IEEE Trans. Speech Audio Process., 2009

Clustering-Based Approach for Predicting Motif Pairs from protein Interaction Data.

Henry Chi-Ming Leung, Man-Hung Siu, Siu-Ming Yiu, Francis Yuk-Lun Chin, Ken Wing-Kin Sung

J. Bioinform. Comput. Biol., 2009

Unsupervised training of an HMM-based speech recognizer for topic classification.

Herbert Gish, Man-Hung Siu, Arthur Chan, William Belfield

Proceedings of the INTERSPEECH 2009, 2009

2008

Evaluation of the robustness of the polynomial segment models to noisy environments with unsupervised adaptation.

Jeff Siu-Kei Au-Yeung, Man-Hung Siu

Speech Commun., 2008

Optimal Algorithm for Finding DNA Motifs with Nucleotide Adjacent Dependency.

Francis Y. L. Chin, Henry C. M. Leung, Man-Hung Siu, Siu-Ming Yiu

Proceedings of the 6th Asia-Pacific Bioinformatics Conference, 2008

2007

Web resources for language modeling in conversational speech recognition.

Ivan Bulyko, Mari Ostendorf, Man-Hung Siu, Tim Ng, Andreas Stolcke, Özgür Çetin

ACM Trans. Speech Lang. Process., 2007

Boosting with anti-models for automatic language identification.

Xi Yang, Man-Hung Siu, Herbert Gish, Brian Mak

Proceedings of the INTERSPEECH 2007, 2007

A model-based estimation of phonotactic language verification performance.

Kakeung Wong, Man-Hung Siu, Brian Mak

Proceedings of the INTERSPEECH 2007, 2007

N-Best Tokenization in a GMM-SVM Language Identification System.

Xi Yang, Man-Hung Siu

Proceedings of the IEEE International Conference on Acoustics, 2007

2006

A Robust Viterbi Algorithm Against Impulsive Noise With Application to Speech Recognition.

Man-Hung Siu, Arthur Chan

IEEE Trans. Speech Audio Process., 2006

Recursive likelihood evaluation and fast search algorithm for polynomial segment model with application to speech recognition.

Chak-Fai Li, Man-Hung Siu, Jeff Siu-Kei Au-Yeung

IEEE Trans. Speech Audio Process., 2006

Minimization of Utterance Verification Error Rate as a Constrained Optimization Problem.

Man-Hung Siu, Brian Mak, Wing-Hei Au

IEEE Signal Process. Lett., 2006

Joint Optimization of the Frequency-Domain and Time-Domain Transformations in Deriving Generalized Static and Dynamic MFCCs.

Yiu-Pong Lai, Man-Hung Siu, Brian Mak

IEEE Signal Process. Lett., 2006

Maximum Likelihood Linear Regression Adaptation for the Polynomial Segment Models.

Jeff Siu-Kei Au-Yeung, Man-Hung Siu

IEEE Signal Process. Lett., 2006

Adaptive articulatory feature-based conditional pronunciation modeling for speaker verification.

Ka-Yee Leung, Man-Wai Mak, Man-Hung Siu, Sun-Yuan Kung

Speech Commun., 2006

Articulatory-feature-based confidence measures.

Ka-Yee Leung, Man-Hung Siu

Comput. Speech Lang., 2006

Discriminatively trained Language Models using Support Vector Machines for Language Identification.

Lu-Feng Zhai, Man-Hung Siu, Xi Yang, Herbert Gish

Proceedings of the Odyssey 2006, 2006

Consistent Modeling of the Static and Time-Derivative Cepstrums for Speech Recognition Using HSPTM.

Yiu-Pong Lai, Man-Hung Siu

Proceedings of the Chinese Spoken Language Processing, 5th International Symposium, 2006

Improved language identification using support vector machines for language modeling.

Xi Yang, Lu-Feng Zhai, Man-Hung Siu, Herbert Gish

Proceedings of the INTERSPEECH 2006, 2006

Improved tone modeling for Mandarin broadcast news speech recognition.

Xin Lei, Man-Hung Siu, Mei-Yuh Hwang, Mari Ostendorf, Tan Lee

Proceedings of the INTERSPEECH 2006, 2006

Robust Large Vocabulary Continuous Speech Recognition using Polynomial Segment Model with Unsupervised Adaptation.

Man-Hung Siu, Jeff Siu-Kei Au-Yeung

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

Reference Speaker Weighting Adaptation for Sub-Phonetic Polynomial Segment Models.

Jeff Siu-Kei Au-Yeung, Man-Hung Siu

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

2005

A quantitative assessment of the importance of tone in mandarin speech recognition.

Tim Ng, Man-Hung Siu, Mari Ostendorf

IEEE Signal Process. Lett., 2005

Efficient computation of the frame-based extended union model and its application in speech recognition against partial temporal corruptions.

Arthur Chan, Man-Hung Siu

Comput. Speech Lang., 2005

High-density discrete HMM with the use of scalar quantization indexing.

Brian Mak, Jeff Siu-Kei Au-Yeung, Yiu-Pong Lai, Man-Hung Siu

Proceedings of the INTERSPEECH 2005, 2005

Speaker verification via articulatory feature-based conditional pronunciation modeling with vowel and consonant mixture models.

Ka-Yee Leung, Man-Wai Mak, Man-Hung Siu, Sun-Yuan Kung

Proceedings of the INTERSPEECH 2005, 2005

Web-Data Augmented Language Models for Mandarin Conversational Speech Recognition.

Tim Ng, Mari Ostendorf, Mei-Yuh Hwang, Man-Hung Siu, Ivan Bulyko, Xin Lei

Proceedings of the 2005 IEEE International Conference on Acoustics, 2005

Speaker Verification Using Adapted Articulatory Feature-based Conditional Pronunciation Modeling.

Ka-Yee Leung, Man-Wai Mak, Man-Hung Siu, Sun-Yuan Kung

Proceedings of the 2005 IEEE International Conference on Acoustics, 2005

Sub-phonetic Polynomial Segment Model for Large Vocabulary Continuous Speech Recognition.

Jeff Siu-Kei Au-Yeung, Chak-Fai Li, Man-Hung Siu

Proceedings of the 2005 IEEE International Conference on Acoustics, 2005

2004

Integration of acoustic and articulatory information with application to speech recognition.

Ka-Yee Leung, Man-Hung Siu

Inf. Fusion, 2004

Adaptive conditional pronunciation modeling using articulatory features for speaker verification.

Ka-Yee Leung, Man-Wai Mak, Man-Hung Siu, Sun-Yuan Kung

Proceedings of the 2004 International Symposium on Chinese Spoken Language Processing, 2004

Progress on Mandarin conversational telephone speech recognition.

Mei-Yuh Hwang, Xin Lei, Tim Ng, Ivan Bulyko, Mari Ostendorf, Andreas Stolcke, Wen Wang, Jing Zheng, Venkata Ramana Rao Gadde, Martin Graciarena, Man-Hung Siu, Yan Huang

Proceedings of the 2004 International Symposium on Chinese Spoken Language Processing, 2004

Automatic language identification using discrete hidden Markov model.

Kakeung Wong, Man-Hung Siu

Proceedings of the INTERSPEECH 2004, 2004

A robust training algorithm based on neighborhood information.

Wing-Hei Au, Man-Hung Siu

Proceedings of the INTERSPEECH 2004, 2004

Improved performance of Aurora 4 using HTK and unsupervised MLLR adaptation.

Jeff Siu-Kei Au-Yeung, Man-Hung Siu

Proceedings of the INTERSPEECH 2004, 2004

Speech recognition enhancement by psychoacoustic modeled noise suppression.

Yiu-Pong Lai, Man-Chun Hui, Chi-Wah Kok, Man-Hung Siu

Proceedings of the 2004 IEEE International Conference on Multimedia and Expo, 2004

Decision tree based tone modeling for Chinese speech recognition.

Pui-Fung Wong, Man-Hung Siu

Proceedings of the 2004 IEEE International Conference on Acoustics, 2004

Training for polynomial segment model using the expectation maximization algorithm.

Chak-Fai Li, Man-Hung Siu

Proceedings of the 2004 IEEE International Conference on Acoustics, 2004

Hidden spectral peak trajectory model for phone classification.

Yiu-Pong Lai, Man-Hung Siu

Proceedings of the 2004 IEEE International Conference on Acoustics, 2004

Discrimination power weighted subword-based speaker verification.

Siu Man Chan, Man-Hung Siu

Proceedings of the 2004 IEEE International Conference on Acoustics, 2004

2003

Maximum likelihood normalization for robust speech recognition.

Yiu-Pong Lai, Man-Hung Siu

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

A new approach to minimize utterance verification error rate for a specific operating point.

Wing-Hei Au, Man-Hung Siu

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

An efficient incremental likelihood evaluation for polynomial trajectory model using with application to model training and recognition.

Chak-Fai Li, Man-Hung Siu

Proceedings of the 2003 IEEE International Conference on Acoustics, 2003

Phone level confidence measure using articulatory features.

Ka-Yee Leung, Man-Hung Siu

Proceedings of the 2003 IEEE International Conference on Acoustics, 2003

2002

Robust speech recognition against short-time noise.

Man-Hung Siu, Yu-Chung Chan

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

Speech recognition using combined acoustic and articulatory information with retraining of acoustic model parameters.

Ka-Yee Leung, Man-Hung Siu

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

Integration of Tone Related Feature for Chinese Speech Recognition.

Pui-Fung Wong, Man-Hung Siu

Proceedings of the 4th IEEE International Conference on Multimodal Interfaces (ICMI 2002), 2002

Speech recognition using multi-state acoustic and articulatory features models with asynchronous states transition.

Ka-Yee Leung, Man-Hung Siu

Proceedings of the IEEE International Conference on Acoustics, 2002

2001

Robust speech recognition against packet loss.

Man-Hung Siu, Yu-Chung Chan

Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

2000

Variable n-grams and extensions for conversational speech language modeling.

Man-Hung Siu, Mari Ostendorf

IEEE Trans. Speech Audio Process., 2000

Computer-aided Mandarin pronunciation learning system.

Man-Hung Siu, Ka-Ming Wong, Man-Yan Ching, Mei-Sum Lau

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

Pruning of state-tying tree using bayesian information criterion with multiple mixtures.

Yu-Chung Chan, Man-Hung Siu, Brian Kan-Wing Mak

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

Integrating a context-dependent phrase grammar in the variable n-gram framework.

Man-Hung Siu, Mari Ostendorf

Proceedings of the IEEE International Conference on Acoustics, 2000

1999

Evaluation of word confidence for speech recognition systems.

Man-Hung Siu, Herbert Gish

Comput. Speech Lang., 1999

Using a large vocabulary continuous speech recognizer for a constrained domain with limited training.

Man-Hung Siu, Michael Jonas, Herbert Gish

Proceedings of the 1999 IEEE International Conference on Acoustics, 1999

Automatic topic identification for two-level call routing.

John Golden, Owen Kimball, Man-Hung Siu, Herbert Gish

Proceedings of the 1999 IEEE International Conference on Acoustics, 1999

Recent experiments in large vocabulary conversational speech recognition.

Jayadev Billa, Thomas Colthurst, Amro El-Jaroudi, Rukmini Iyer, Kristine W. Ma, Spyridon Matsoukas, Carl Quillen, Fred Richardson, Man-Hung Siu, George Zavaliagkos, Herbert Gish

Proceedings of the 1999 IEEE International Conference on Acoustics, 1999

1998

Using untranscribed training data to improve performance.

George Zavaliagkos, Man-Hung Siu, Thomas Colthurst, Jayadev Billa

Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

Parametric trajectory mixtures for LVCSR.

Man-Hung Siu, Rukmini Iyer, Herbert Gish, Carl Quillen

Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

Hidden Markov models for trajectory modeling.

Rukmini Iyer, Herbert Gish, Man-Hung Siu, George Zavaliagkos, Spyros Matsoukas

Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

The BBN Byblos 1997 large vocabulary conversational speech recognition system.

George Zavaliagkos, John W. McDonough, David R. Miller, Amro El-Jaroudi, Jayadev Billa, Fred Richardson, Kristine W. Ma, Man-Hung Siu, Herbert Gish

Proceedings of the 1998 IEEE International Conference on Acoustics, 1998

1997

Variable n-gram language modeling and extensions for conversational speech.

Man-Hung Siu, Mari Ostendorf

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

Improved estimation, evaluation and applications of confidence measures for speech recognition.

Man-Hung Siu, Herbert Gish, Fred Richardson

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

1996

Modeling disfluencies in conversational speech.

Man-Hung Siu, Mari Ostendorf

Proceedings of the 4th International Conference on Spoken Language Processing, 1996

1995

Large vocabulary word scoring as a basis for transcription generation.

Philippe Jeanrenaud, Man-Hung Siu, Herbert Gish

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

Reducing word error rate on conversational speech from the Switchboard corpus.

Philippe Jeanrenaud, Ellen Eide, Upendra V. Chaudhari, John W. McDonough, Kenney Ng, Man-Hung Siu, Herbert Gish

Proceedings of the 1995 International Conference on Acoustics, 1995

1994

Predicting word spotting performance.

Man-Hung Siu, Herbert Gish, Jan Robin Rohlicek

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

Spotting events in continuous speech.

Philippe Jeanrenaud, Man-Hung Siu, Jan Robin Rohlicek, Marie Meteer, Herbert Gish

Proceedings of ICASSP '94: IEEE International Conference on Acoustics, 1994

An invariance property of neural networks.

Herbert Gish, Man-Hung Siu

Proceedings of ICASSP '94: IEEE International Conference on Acoustics, 1994

1993

Phonetic-based word spotter: various configurations and application to event spotting.

Philippe Jeanrenaud, Kenney Ng, Man-Hung Siu, Jan Robin Rohlicek, Herbert Gish

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

Phonetic training and language modeling for word spotting.

Jan Robin Rohlicek, Philippe Jeanrenaud, Kenney Ng, Herbert Gish, Bruce R. Musicus, Man-Hung Siu

Proceedings of the IEEE International Conference on Acoustics, 1993

Gisting conversational speech in real time.

L. Denenberg, Herbert Gish, Marie Meteer, T. Miller, Jan Robin Rohlicek, W. Sadkin, Man-Hung Siu

Proceedings of the IEEE International Conference on Acoustics, 1993

1992

An unsupervised, sequential learning algorithm for the segmentation of speech waveforms with multiple speakers.

Man-Hung Siu, George Yu, Herbert Gish

Proceedings of the 1992 IEEE International Conference on Acoustics, 1992

Gisting conversational speech.

Jan Robin Rohlicek, Damaris M. Ayuso, Madeleine Bates, Robert J. Bobrow, A. Boulanger, Herbert Gish, Philippe Jeanrenaud, Marie Meteer, Man-Hung Siu

Proceedings of the 1992 IEEE International Conference on Acoustics, 1992

1991

Segregation of speakers for speech recognition and speaker identification.

Herbert Gish, Man-Hung Siu, Jan Robin Rohlicek

Proceedings of the 1991 International Conference on Acoustics, 1991