Mei-Yuh Hwang

发表

Speed up of recurrent neural network language models with sentence independent subsampling stochastic gradient descent

Yangyang Shi, Mei-Yuh Hwang, Kaisheng Yao, 2013, INTERSPEECH.

RNN-based labeled data generation for spoken language understanding

Yangyang Shi, Mei-Yuh Hwang, Yik-Cheung Tam, 2015, INTERSPEECH.

Cross-Domain and Cross-Language Portability of Acoustic Features Estimated by Multilayer Perceptrons

Andreas Stolcke, Mei-Yuh Hwang, Dimitra Vergyri, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

Applying SPHINX-II to the DARPA Wall Street Journal CSR Task

Mei-Yuh Hwang, Ronald Rosenfeld, Xuedong Huang, 1992, HLT.

Source Critical Reinforcement Learning for Transferring Spoken Language Understanding to a New Language

Mei-Yuh Hwang, Yu Zhou, Jiajun Zhang, 2018, COLING.

Improved Hidden Markov Modeling for Speaker-Independent Continuous Speech Recognition

Mei-Yuh Hwang, Satoru Hayamizu, Xuedong Huang, 1990, HLT.

Incremental Training and Intentional Over-fitting of Word Alignment

Mei-Yuh Hwang, Qin Gao, Chris Quirk, 2011 .

Improved tone modeling for Mandarin broadcast news speech recognition

Mei-Yuh Hwang, Mari Ostendorf, Tan Lee, 2006, INTERSPEECH.

Semi-supervised slot tagging in spoken language understanding using recurrent transductive support vector machines

Yangyang Shi, Mei-Yuh Hwang, Kaisheng Yao, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

Microsoft Windows highly intelligent speech recognizer: Whisper

Mei-Yuh Hwang, Alex Acero, Xuedong Huang, 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

An Overview of the SPHINX-II Speech Recognition System

Mei-Yuh Hwang, Ronald Rosenfeld, Xuedong Huang, 1993, HLT.

An improved search algorithm using incremental knowledge for continuous speech recognition

Mei-Yuh Hwang, Xuedong Huang, Fil Alleva, 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Deleted interpolation and density sharing for continuous hidden Markov models

Mei-Yuh Hwang, Xuedong Huang, Li Jiang, 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

A Teacher-Student Framework for Maintainable Dialog Manager

Mei-Yuh Hwang, Han Zhang, Jiajun Zhang, 2018, EMNLP.

From CMU Sphinx-II to Microsoft Whisper: Making Speech Recognition Usable

Mei-Yuh Hwang, Xuedong Huang, Doug Beeferman, 1994 .

Web-data augmented language models for Mandarin conversational speech recognition

Mei-Yuh Hwang, Mari Ostendorf, Man-Hung Siu, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Recurrent Support Vector Machines For Slot Tagging In Spoken Language Understanding

Yangyang Shi, Mei-Yuh Hwang, Kaisheng Yao, 2016, HLT-NAACL.

Subphonetic Modeling for Speech Recognition

Mei-Yuh Hwang, Xuedong Huang, M. Hwang, 1992, HLT.

Knowledge Distillation for Recurrent Neural Network Language Modeling with Trust Regularization

Yangyang Shi, Mei-Yuh Hwang, Xin Lei, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Senones, multi-pass search, and unified stochastic modeling in sphinx-II

Mei-Yuh Hwang, Xuedong Huang, Fil Alleva, 1993, EUROSPEECH.

Progress on Mandarin conversational telephone speech recognition

Andreas Stolcke, Wen Wang, Mei-Yuh Hwang, 2004, 2004 International Symposium on Chinese Spoken Language Processing.

Multiple beamformers with ROVER for the CHiME-5 Challenge

Lei Xie, Yangyang Shi, Mei-Yuh Hwang, 2018, 5th International Workshop on Speech Processing in Everyday Environments (CHiME 2018).

Cluster based Chinese abbreviation modeling

Yangyang Shi, Mei-Yuh Hwang, Yi-Cheng Pan, 2014, INTERSPEECH.

Parsing-based objective functions for speech recognition in translation applications

Mary P. Harper, Mei-Yuh Hwang, Mari Ostendorf, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Predicting unseen triphones with senones

Mei-Yuh Hwang, Xuedong Huang, Fil Alleva, 1996, IEEE Trans. Speech Audio Process..

Large-Scale Thai Statistical Machine Translation

Mei-Yuh Hwang, Lee Schwartz, Glenn Slayden, 2010 .

Speech recognition system for recognizing continuous speech and isolated

Mei-Yuh Hwang, Li Jiang, A. Fileno Alleva, 1998 .

Generating large graphoneme units criterion mutual information for speech synthesis

Mei-Yuh Hwang, Li Jiang, 2005 .

Combining Discriminative Feature, Transform, and Model Training for Large Vocabulary Speech Recognition

Andreas Stolcke, Mei-Yuh Hwang, Jing Zheng, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Unified stochastic engine (USE) for speech recognition

Mei-Yuh Hwang, Xuedong Huang, Fil Alleva, 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Porting Decipher from English to Mandarin

Andreas Stolcke, Mei-Yuh Hwang, Mari Ostendorf, 2006 .

From Sphinx-II to Whisper — Making Speech Recognition Usable

Mei-Yuh Hwang, Xuedong Huang, Li Jiang, 1996 .

The SPHINX speech recognition system

Mei-Yuh Hwang, Hsiao-Wuen Hon, Raj Reddy, 1989, International Conference on Acoustics, Speech, and Signal Processing,.

Acoustic distribution clustering in phonetic hidden Markov models

Mei-Yuh Hwang, Xuedong Huang, 1991, EUROSPEECH.

Speech recognition using hidden Markov models: A CMU perspective

Mei-Yuh Hwang, Xuedong Huang, Hsiao-Wuen Hon, 1990, Speech Commun..

ACOUSTIC MODELING FOR MANDARIN LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION

Mei-Yuh Hwang, 2006 .

The MSR SYSTEM for IWSLT 2011 evaluation

Mei-Yuh Hwang, Li Deng, Alex Acero, 2011, IWSLT.

Speech Understanding in Open Tasks

Mei-Yuh Hwang, Xuedong Huang, Hsiao-Wuen Hon, 1992, HLT.

Leave-One-Out Phrase Model Training for Large-Scale Deployment

Mei-Yuh Hwang, Chris Quirk, Joern Wuebker, 2012, WMT@NAACL-HLT.

Building a highly accurate Mandarin speech recognizer

Wen Wang, Mei-Yuh Hwang, Mari Ostendorf, 2007, 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU).

Subphonetic modeling with Markov states-Senone

Mei-Yuh Hwang, Xuedong Huang, 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

The SPHINX-II speech recognition system: an overview

Mei-Yuh Hwang, Ronald Rosenfeld, Xuedong Huang, 1993, Comput. Speech Lang..

Recurrent neural networks for language understanding

Geoffrey Zweig, Yangyang Shi, Mei-Yuh Hwang, 2013, INTERSPEECH.

Incorporating tone-related MLP posteriors in the feature representation for Mandarin ASR

Mei-Yuh Hwang, Mari Ostendorf, Xin Lei, 2005, INTERSPEECH.

Training Augmentation with Adversarial Examples for Robust Speech Recognition pdf

Mei-Yuh Hwang, Lei Xie, Mari Ostendorf, 2018, INTERSPEECH.

Thai Sentence-Breaking for Large-Scale SMT

Mei-Yuh Hwang, Lee Schwartz, Glenn Slayden, 2010 .

Contextual spoken language understanding using recurrent neural networks

Yangyang Shi, Mei-Yuh Hwang, Kaisheng Yao, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Shared-distribution hidden Markov models for speech recognition

Mei-Yuh Hwang, Xuedong Huang, M. Hwang, 1993, IEEE Trans. Speech Audio Process..

Adversarial Regularization for Attention Based End-to-End Robust Speech Recognition

Mei-Yuh Hwang, Lei Xie, Pengcheng Guo, 2019, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Building A Highly Accurate Mandarin Speech Recognizer With Language-Independent Technologies and Language-Dependent Modules

Wen Wang, Mei-Yuh Hwang, Mari Ostendorf, 2009, IEEE Transactions on Audio, Speech, and Language Processing.

A Robust Nonlinear Microphone Array Postfilter for Noise Reduction

Mei-Yuh Hwang, Yunxin Zhao, Sining Sun, 2018, 2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC).

Investigation on Mandarin broadcast news speech recognition

Wen Wang, Mei-Yuh Hwang, Xin Lei, 2006, INTERSPEECH.

End-to-end Speech Recognition Using a High Rank LSTM-CTC Based Model

Yangyang Shi, Mei-Yuh Hwang, Xin Lei, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Recent progress and future outlook of the SPHINX speech recognition system

Mei-Yuh Hwang, Hsiao-Wuen Hon, Kai-Fu Lee, 1990 .

Automatic acoustic segmentation for speech recognition on broadcast recordings

Mei-Yuh Hwang, Mari Ostendorf, Gang Peng, 2007, INTERSPEECH.

Can continuous speech recognizers handle isolated speech?

Mei-Yuh Hwang, Xuedong Huang, Li Jiang, 1997, Speech Commun..

Improving speech recognition performance via phone-dependent VQ codebooks and adaptive language models in SPHINX-II

Mei-Yuh Hwang, Ronald Rosenfeld, Xuedong Huang, 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

Improved acoustic modeling with the SPHINX speech recognition system

Mei-Yuh Hwang, Xuedong Huang, K.-F. Lee, 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

Incremental Learning from Scratch for Task-Oriented Dialogue Systems

Mei-Yuh Hwang, Jiajun Zhang, Chengqing Zong, 2019, ACL.

Predicting unseen triphones with senones

Mei-Yuh Hwang, Xuedong Huang, Fil Alleva, 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Region Proposal Network Based Small-Footprint Keyword Spotting

Mei-Yuh Hwang, Mari Ostendorf, Lei Xie, 2019, IEEE Signal Processing Letters.

Domain Adversarial Training for Accented Speech Recognition

Mei-Yuh Hwang, Lei Xie, Mari Ostendorf, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improvements on the pronunciation prefix tree search organization

Mei-Yuh Hwang, Xuedong Huang, Fil Alleva, 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

Improvements on speech recognition for fast talkers

Mei-Yuh Hwang, Matthew Richardson, Alex Acero, 1999, EUROSPEECH.

Mining Effective Negative Training Samples for Keyword Spotting

Mei-Yuh Hwang, Mari Ostendorf, Lei Xie, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multiple fixed beamformers with a spacial Wiener-form postfilter for far-field speech recognition

Lei Xie, Mei-Yuh Hwang, Qin Li, 2019, 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Dynamically configurable acoustic models for speech recognition

Mei-Yuh Hwang, Xuedong Huang, 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

Recent innovations in speech-to-text transcription at SRI-ICSI-UW

Andreas Stolcke, Wen Wang, Mei-Yuh Hwang, 2006, IEEE Transactions on Audio, Speech, and Language Processing.

A comparative study of discrete, semicontinuous, and continuous hidden Markov models

Mei-Yuh Hwang, Xuedong Huang, Hsiao-Wuen Hon, 1993, Comput. Speech Lang..

Speech recognition using hidden Markov models: A CMU perspective

Mei-Yuh Hwang, Xuedong Huang, Hsiao-Wuen Hon, 1990, Speech Communication.

Unsupervised learning from users' error correction in speech dictation

Mei-Yuh Hwang, Dong Yu, Li Deng, 2004, INTERSPEECH.

Method and apparatus for dynamically-adjusted training for speech recognition

Mei-Yuh Hwang, Hsiao-Wuen Hon, Li Jiang, 1997 .

Modeling between-word coarticulation in continuous speech recognition

Mei-Yuh Hwang, Hsiao-Wuen Hon, Kai-Fu Lee, 1989, EUROSPEECH.