default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDMan-Hung Siu
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[c76]Zhihong Lei, Ernest Pusateri, Shiyi Han, Leo Liu, Mingbin Xu, Tim Ng, Ruchir Travadi, Youyuan Zhang, Mirko Hannemann, Man-Hung Siu, Zhen Huang:
Personalization of CTC-Based End-to-End Speech Recognition Using Pronunciation-Driven Subword Tokenization. ICASSP 2024: 10096-10100- [i5]Iwen E. Kang, Christophe Van Gysel, Man-Hung Siu:
Transformer-based Model for ASR N-Best Rescoring and Rewriting. CoRR abs/2406.08207 (2024) - 2023
- [c75]Zhihong Lei, Mingbin Xu, Shiyi Han, Leo Liu, Zhen Huang, Tim Ng, Yuanyuan Zhang, Ernest Pusateri, Mirko Hannemann, Yaqiao Deng, Man-Hung Siu:
Acoustic Model Fusion For End-to-End Speech Recognition. ASRU 2023: 1-7 - [i4]Zhihong Lei, Mingbin Xu, Shiyi Han, Leo Liu, Zhen Huang, Tim Ng, Yuanyuan Zhang, Ernest Pusateri, Mirko Hannemann, Yaqiao Deng, Man-Hung Siu:
Acoustic Model Fusion for End-to-end Speech Recognition. CoRR abs/2310.07062 (2023) - [i3]Zhihong Lei, Ernest Pusateri, Shiyi Han, Leo Liu, Mingbin Xu, Tim Ng, Ruchir Travadi, Youyuan Zhang, Mirko Hannemann, Man-Hung Siu, Zhen Huang:
Personalization of CTC-based End-to-End Speech Recognition Using Pronunciation-Driven Subword Tokenization. CoRR abs/2310.09988 (2023) - 2020
- [c74]Herbert Gish, Jan Silovský, Man-Ling Sung, Man-Hung Siu, William Hartmann, Zhuolin Jiang:
Towards a New Understanding of the Training of Neural Networks with Mislabeled Training Data. ICASSP 2020: 8394-8398 - [i2]Zhuolin Jiang, Jan Silovský, Man-Hung Siu, William Hartmann, Herbert Gish, Sancar Adali:
Learning from Noisy Labels with Noise Modeling Network. CoRR abs/2005.00596 (2020)
2010 – 2019
- 2019
- [i1]Herbert Gish, Jan Silovský, Man-Ling Sung, Man-Hung Siu, William Hartmann, Zhuolin Jiang:
Towards a New Understanding of the Training of Neural Networks with Mislabeled Training Data. CoRR abs/1909.09136 (2019) - 2018
- [c73]Francis Keith, William Hartmann, Man-Hung Siu, Jeff Z. Ma, Owen Kimball:
Optimizing Multilingual Knowledge Transfer for Time-Delay Neural Networks with Low-Rank Factorization. ICASSP 2018: 4924-4928 - 2017
- [c72]Roger Hsiao, Tim Ng, Man-Hung Siu:
Unsupervised adaptation for deep neural networks using Alternating Direction Method of Multipliers. ICASSP 2017: 5180-5184 - [c71]William Hartmann, Roger Hsiao, Tim Ng, Jeff Z. Ma, Francis Keith, Man-Hung Siu:
Improved Single System Conversational Telephone Speech Recognition with VGG Bottleneck Features. INTERSPEECH 2017: 112-116 - [c70]Jeff Z. Ma, Francis Keith, Tim Ng, Man-Hung Siu, Owen Kimball:
Improving Deliverable Speech-to-Text Systems with Multilingual Knowledge Transfer. INTERSPEECH 2017: 127-131 - 2016
- [c69]Kerri Barnes, Matthew Snover, Man-Hung Siu, Herbert Gish:
Importance sampling of delta-AUC: A basis for active learning for improved keyword search. ICASSP 2016: 2244-2248 - [c68]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:
Sage: The New BBN Speech Processing Platform. INTERSPEECH 2016: 3022-3026 - 2015
- [c67]Jeff Z. Ma, Jan Silovský, Man-Hung Siu, Owen Kimball:
Large-scale speaker search using PLDA on mismatched conditions. ICASSP 2015: 1846-1850 - 2014
- [j17]Man-Hung Siu, Herbert Gish, Arthur Chan, William Belfield, Steve Lowe:
Unsupervised training of an HMM-based self-organizing unit recognizer with applications to topic classification and keyword discovery. Comput. Speech Lang. 28(1): 210-223 (2014) - 2012
- [c66]Man-Hung Siu, Omer Lang, Herbert Gish, Stephen A. Lowe, Arthur Chan, Owen Kimball:
MLLR transforms of self-organized units as features in speaker recognition. ICASSP 2012: 4385-4388 - [c65]Ivan Bulyko, Owen Kimball, Man-Hung Siu, Jose Herrero, Dan Blum:
Detection of unseen words in conversational Mandarin. ICASSP 2012: 5181-5184 - 2011
- [c64]Timothy J. Hazen, Man-Hung Siu, Herbert Gish, Steve Lowe, Arthur Chan:
Topic modeling for spoken documents using only phonetic information. ASRU 2011: 395-400 - [c63]Man-Hung Siu, Herbert Gish, Steve Lowe, Arthur Chan:
Unsupervised Audio Patterns Discovery Using HMM-Based Self-Organized Units. INTERSPEECH 2011: 2333-2336 - 2010
- [c62]Man-Hung Siu, Herbert Gish, Arthur Chan, William Belfield:
Improved topic classification and keyword discovery using an HMM-based speech recognizer trained without supervision. INTERSPEECH 2010: 2838-2841 - [c61]Man-Hung Siu, Ted Vessenes, Ivan Bulyko, Owen Kimball:
Improved named entity extraction from conversational speech with language model adaptation. SLT 2010: 418-423
2000 – 2009
- 2009
- [j16]Henry Chi-Ming Leung, Man-Hung Siu, Siu-Ming Yiu, Francis Yuk-Lun Chin, Ken Wing-Kin Sung:
Clustering-Based Approach for Predicting Motif Pairs from protein Interaction Data. J. Bioinform. Comput. Biol. 7(4): 701-716 (2009) - [j15]Man-Hung Siu, Xi Yang, Herbert Gish:
Discriminatively Trained GMMs for Language Classification Using Boosting Methods. IEEE Trans. Speech Audio Process. 17(1): 187-197 (2009) - [c60]Herbert Gish, Man-Hung Siu, Arthur Chan, William Belfield:
Unsupervised training of an HMM-based speech recognizer for topic classification. INTERSPEECH 2009: 1935-1938 - 2008
- [j14]Jeff Siu-Kei Au-Yeung, Man-Hung Siu:
Evaluation of the robustness of the polynomial segment models to noisy environments with unsupervised adaptation. Speech Commun. 50(10): 769-781 (2008) - [c59]Francis Y. L. Chin, Henry C. M. Leung, Man-Hung Siu, Siu-Ming Yiu:
Optimal Algorithm for Finding DNA Motifs with Nucleotide Adjacent Dependency. APBC 2008: 343-352 - 2007
- [j13]Ivan Bulyko, Mari Ostendorf, Man-Hung Siu, Tim Ng, Andreas Stolcke, Özgür Çetin:
Web resources for language modeling in conversational speech recognition. ACM Trans. Speech Lang. Process. 5(1): 1:1-1:25 (2007) - [c58]Xi Yang, Man-Hung Siu:
N-Best Tokenization in a GMM-SVM Language Identification System. ICASSP (4) 2007: 1005-1008 - [c57]Kakeung Wong, Man-Hung Siu, Brian Mak:
A model-based estimation of phonotactic language verification performance. INTERSPEECH 2007: 186-189 - [c56]Xi Yang, Man-Hung Siu, Herbert Gish, Brian Mak:
Boosting with anti-models for automatic language identification. INTERSPEECH 2007: 342-345 - 2006
- [j12]Ka-Yee Leung, Man-Hung Siu:
Articulatory-feature-based confidence measures. Comput. Speech Lang. 20(4): 542-562 (2006) - [j11]Ka-Yee Leung, Man-Wai Mak, Man-Hung Siu, Sun-Yuan Kung:
Adaptive articulatory feature-based conditional pronunciation modeling for speaker verification. Speech Commun. 48(1): 71-84 (2006) - [j10]Jeff Siu-Kei Au-Yeung, Man-Hung Siu:
Maximum Likelihood Linear Regression Adaptation for the Polynomial Segment Models. IEEE Signal Process. Lett. 13(10): 644-647 (2006) - [j9]Yiu-Pong Lai, Man-Hung Siu, Brian Mak:
Joint Optimization of the Frequency-Domain and Time-Domain Transformations in Deriving Generalized Static and Dynamic MFCCs. IEEE Signal Process. Lett. 13(11): 707-710 (2006) - [j8]Man-Hung Siu, Brian Mak, Wing-Hei Au:
Minimization of Utterance Verification Error Rate as a Constrained Optimization Problem. IEEE Signal Process. Lett. 13(12): 760-763 (2006) - [j7]Chak-Fai Li, Man-Hung Siu, Jeff Siu-Kei Au-Yeung:
Recursive likelihood evaluation and fast search algorithm for polynomial segment model with application to speech recognition. IEEE Trans. Speech Audio Process. 14(5): 1704-1718 (2006) - [j6]Man-Hung Siu, Arthur Chan:
A Robust Viterbi Algorithm Against Impulsive Noise With Application to Speech Recognition. IEEE Trans. Speech Audio Process. 14(6): 2122-2133 (2006) - [c55]Jeff Siu-Kei Au-Yeung, Man-Hung Siu:
Reference Speaker Weighting Adaptation for Sub-Phonetic Polynomial Segment Models. ICASSP (1) 2006: 233-236 - [c54]Man-Hung Siu, Jeff Siu-Kei Au-Yeung:
Robust Large Vocabulary Continuous Speech Recognition using Polynomial Segment Model with Unsupervised Adaptation. ICASSP (1) 2006: 449-452 - [c53]Xin Lei, Man-Hung Siu, Mei-Yuh Hwang, Mari Ostendorf, Tan Lee:
Improved tone modeling for Mandarin broadcast news speech recognition. INTERSPEECH 2006 - [c52]Xi Yang, Lu-Feng Zhai, Man-Hung Siu, Herbert Gish:
Improved language identification using support vector machines for language modeling. INTERSPEECH 2006 - [c51]Yiu-Pong Lai, Man-Hung Siu:
Consistent Modeling of the Static and Time-Derivative Cepstrums for Speech Recognition Using HSPTM. ISCSLP (Selected Papers) 2006: 303-314 - [c50]Lu-Feng Zhai, Man-Hung Siu, Xi Yang, Herbert Gish:
Discriminatively trained Language Models using Support Vector Machines for Language Identification. Odyssey 2006: 1-6 - 2005
- [j5]Arthur Chan, Man-Hung Siu:
Efficient computation of the frame-based extended union model and its application in speech recognition against partial temporal corruptions. Comput. Speech Lang. 19(3): 301-319 (2005) - [j4]Tim Ng, Man-Hung Siu, Mari Ostendorf:
A quantitative assessment of the importance of tone in mandarin speech recognition. IEEE Signal Process. Lett. 12(12): 867-870 (2005) - [c49]Ka-Yee Leung, Man-Wai Mak, Man-Hung Siu, Sun-Yuan Kung:
Speaker Verification Using Adapted Articulatory Feature-based Conditional Pronunciation Modeling. ICASSP (1) 2005: 181-184 - [c48]Jeff Siu-Kei Au-Yeung, Chak-Fai Li, Man-Hung Siu:
Sub-phonetic Polynomial Segment Model for Large Vocabulary Continuous Speech Recognition. ICASSP (1) 2005: 193-196 - [c47]Tim Ng, Mari Ostendorf, Mei-Yuh Hwang, Man-Hung Siu, Ivan Bulyko, Xin Lei:
Web-Data Augmented Language Models for Mandarin Conversational Speech Recognition. ICASSP (1) 2005: 589-592 - [c46]Brian Mak, Jeff Siu-Kei Au-Yeung, Yiu-Pong Lai, Man-Hung Siu:
High-density discrete HMM with the use of scalar quantization indexing. INTERSPEECH 2005: 2121-2124 - [c45]Ka-Yee Leung, Man-Wai Mak, Man-Hung Siu, Sun-Yuan Kung:
Speaker verification via articulatory feature-based conditional pronunciation modeling with vowel and consonant mixture models. INTERSPEECH 2005: 3089-3092 - 2004
- [j3]Ka-Yee Leung, Man-Hung Siu:
Integration of acoustic and articulatory information with application to speech recognition. Inf. Fusion 5(2): 141-151 (2004) - [c44]Siu Man Chan, Man-Hung Siu:
Discrimination power weighted subword-based speaker verification. ICASSP (1) 2004: 45-48 - [c43]Chak-Fai Li, Man-Hung Siu:
Training for polynomial segment model using the expectation maximization algorithm. ICASSP (1) 2004: 841-844 - [c42]Pui-Fung Wong, Man-Hung Siu:
Decision tree based tone modeling for Chinese speech recognition. ICASSP (1) 2004: 905-908 - [c41]Yiu-Pong Lai, Man-Hung Siu:
Hidden spectral peak trajectory model for phone classification. ICASSP (1) 2004: 909-912 - [c40]Yiu-Pong Lai, Man-Chun Hui, Chi-Wah Kok, Man-Hung Siu:
Speech recognition enhancement by psychoacoustic modeled noise suppression. ICME 2004: 1335-1338 - [c39]Wing-Hei Au, Man-Hung Siu:
A robust training algorithm based on neighborhood information. INTERSPEECH 2004: 153-156 - [c38]Jeff Siu-Kei Au-Yeung, Man-Hung Siu:
Improved performance of Aurora 4 using HTK and unsupervised MLLR adaptation. INTERSPEECH 2004: 161-164 - [c37]Kakeung Wong, Man-Hung Siu:
Automatic language identification using discrete hidden Markov model. INTERSPEECH 2004: 1633-1636 - [c36]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:
Progress on Mandarin conversational telephone speech recognition. ISCSLP 2004: 1-4 - [c35]Ka-Yee Leung, Man-Wai Mak, Man-Hung Siu, Sun-Yuan Kung:
Adaptive conditional pronunciation modeling using articulatory features for speaker verification. ISCSLP 2004: 61-64 - [e1]Qiang Huo, Man-Hung Siu:
2004 International Symposium on Chinese Spoken Language Processing, ISCSLP 2004, Hong Kong, December 15-18, 2004. IEEE 2004, ISBN 0-7803-8678-7 [contents] - 2003
- [c34]Ka-Yee Leung, Man-Hung Siu:
Phone level confidence measure using articulatory features. ICASSP (1) 2003: 600-603 - [c33]Chak-Fai Li, Man-Hung Siu:
An efficient incremental likelihood evaluation for polynomial trajectory model using with application to model training and recognition. ICASSP (1) 2003: 756-759 - [c32]Yiu-Pong Lai, Man-Hung Siu:
Maximum likelihood normalization for robust speech recognition. INTERSPEECH 2003: 13-16 - [c31]Wing-Hei Au, Man-Hung Siu:
A new approach to minimize utterance verification error rate for a specific operating point. INTERSPEECH 2003: 909-912 - 2002
- [c30]Ka-Yee Leung, Man-Hung Siu:
Speech recognition using multi-state acoustic and articulatory features models with asynchronous states transition. ICASSP 2002: 4163 - [c29]Pui-Fung Wong, Man-Hung Siu:
Integration of Tone Related Feature for Chinese Speech Recognition. ICMI 2002: 64-68 - [c28]Man-Hung Siu, Yu-Chung Chan:
Robust speech recognition against short-time noise. INTERSPEECH 2002: 1049-1052 - [c27]Ka-Yee Leung, Man-Hung Siu:
Speech recognition using combined acoustic and articulatory information with retraining of acoustic model parameters. INTERSPEECH 2002: 2117-2120 - [c26]Pui-Fung Wong, Man-Hung Siu:
Integration of tone related feature for Mandarin speech recognition by a one-pass search algorithm. ISCSLP 2002 - 2001
- [c25]Man-Hung Siu, Yu-Chung Chan:
Robust speech recognition against packet loss. INTERSPEECH 2001: 1095-1098 - 2000
- [j2]Man-Hung Siu, Mari Ostendorf:
Variable n-grams and extensions for conversational speech language modeling. IEEE Trans. Speech Audio Process. 8(1): 63-75 (2000) - [c24]Man-Hung Siu, Mari Ostendorf:
Integrating a context-dependent phrase grammar in the variable n-gram framework. ICASSP 2000: 1643-1646 - [c23]Man-Hung Siu, Ka-Ming Wong, Man-Yan Ching, Mei-Sum Lau:
Computer-aided Mandarin pronunciation learning system. INTERSPEECH 2000: 77-80 - [c22]Yu-Chung Chan, Man-Hung Siu, Brian Kan-Wing Mak:
Pruning of state-tying tree using bayesian information criterion with multiple mixtures. INTERSPEECH 2000: 294-297
1990 – 1999
- 1999
- [j1]Man-Hung Siu, Herbert Gish:
Evaluation of word confidence for speech recognition systems. Comput. Speech Lang. 13(4): 299-319 (1999) - [c21]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:
Recent experiments in large vocabulary conversational speech recognition. ICASSP 1999: 41-44 - [c20]Man-Hung Siu, Michael Jonas, Herbert Gish:
Using a large vocabulary continuous speech recognizer for a constrained domain with limited training. ICASSP 1999: 105-108 - [c19]John Golden, Owen Kimball, Man-Hung Siu, Herbert Gish:
Automatic topic identification for two-level call routing. ICASSP 1999: 509-512 - 1998
- [c18]George Zavaliagkos, John W. McDonough, David R. Miller, Amro El-Jaroudi, Jayadev Billa, Fred Richardson, Kristine W. Ma, Man-Hung Siu, Herbert Gish:
The BBN Byblos 1997 large vocabulary conversational speech recognition system. ICASSP 1998: 905-908 - [c17]Rukmini Iyer, Herbert Gish, Man-Hung Siu, George Zavaliagkos, Spyros Matsoukas:
Hidden Markov models for trajectory modeling. ICSLP 1998 - [c16]Man-Hung Siu, Rukmini Iyer, Herbert Gish, Carl Quillen:
Parametric trajectory mixtures for LVCSR. ICSLP 1998 - [c15]George Zavaliagkos, Man-Hung Siu, Thomas Colthurst, Jayadev Billa:
Using untranscribed training data to improve performance. ICSLP 1998 - 1997
- [c14]Man-Hung Siu, Herbert Gish, Fred Richardson:
Improved estimation, evaluation and applications of confidence measures for speech recognition. EUROSPEECH 1997: 831-834 - [c13]Man-Hung Siu, Mari Ostendorf:
Variable n-gram language modeling and extensions for conversational speech. EUROSPEECH 1997: 2739-2742 - 1996
- [c12]Man-Hung Siu, Mari Ostendorf:
Modeling disfluencies in conversational speech. ICSLP 1996: 386-389 - 1995
- [c11]Philippe Jeanrenaud, Ellen Eide, Upendra V. Chaudhari, John W. McDonough, Kenney Ng, Man-Hung Siu, Herbert Gish:
Reducing word error rate on conversational speech from the Switchboard corpus. ICASSP 1995: 53-56 - [c10]Philippe Jeanrenaud, Man-Hung Siu, Herbert Gish:
Large vocabulary word scoring as a basis for transcription generation. EUROSPEECH 1995: 2149-2152 - 1994
- [c9]Philippe Jeanrenaud, Man-Hung Siu, Jan Robin Rohlicek, Marie Meteer, Herbert Gish:
Spotting events in continuous speech. ICASSP (1) 1994: 381-384 - [c8]Herbert Gish, Man-Hung Siu:
An invariance property of neural networks. ICASSP (2) 1994: 541-544 - [c7]Man-Hung Siu, Herbert Gish, Jan Robin Rohlicek:
Predicting word spotting performance. ICSLP 1994: 2195-2198 - 1993
- [c6]L. Denenberg, Herbert Gish, Marie Meteer, T. Miller, Jan Robin Rohlicek, W. Sadkin, Man-Hung Siu:
Gisting conversational speech in real time. ICASSP (2) 1993: 131-134 - [c5]Jan Robin Rohlicek, Philippe Jeanrenaud, Kenney Ng, Herbert Gish, Bruce R. Musicus, Man-Hung Siu:
Phonetic training and language modeling for word spotting. ICASSP (2) 1993: 459-462 - [c4]Philippe Jeanrenaud, Kenney Ng, Man-Hung Siu, Jan Robin Rohlicek, Herbert Gish:
Phonetic-based word spotter: various configurations and application to event spotting. EUROSPEECH 1993: 1057-1060 - 1992
- [c3]Jan Robin Rohlicek, Damaris M. Ayuso, Madeleine Bates, Robert J. Bobrow, A. Boulanger, Herbert Gish, Philippe Jeanrenaud, Marie Meteer, Man-Hung Siu:
Gisting conversational speech. ICASSP 1992: 113-116 - [c2]Man-Hung Siu, George Yu, Herbert Gish:
An unsupervised, sequential learning algorithm for the segmentation of speech waveforms with multiple speakers. ICASSP 1992: 189-192 - 1991
- [c1]Herbert Gish, Man-Hung Siu, Jan Robin Rohlicek:
Segregation of speakers for speech recognition and speaker identification. ICASSP 1991: 873-876
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-09-28 01:27 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
