Khe Chai Sim

发表

Improving the efficiency of forward-backward algorithm using batched computation in TensorFlow

Tara N. Sainath, Arun Narayanan, Khe Chai Sim, 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

On Acoustic Diversification Front-End for Spoken Language Identification

Haizhou Li, Khe Chai Sim, Haizhou Li, 2008, IEEE Transactions on Audio, Speech, and Language Processing.

An Efficient Phone N-Gram Forward-Backward Computation Using Dense Matrix Multiplication

Arun Narayanan, Khe Chai Sim, K. Sim, 2017, INTERSPEECH.

Learning Factorized Transforms for Unsupervised Adaptation of LSTM-RNN Acoustic Models

Khe Chai Sim, Brian Kan-Wing Mak, Lahiru Samarakoon, 2017, INTERSPEECH.

An investigation of tied-mixture GMM based triphone state clustering

Guangsen Wang, Khe Chai Sim, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Acoustic Modeling for Google Home

Mitch Weintraub, Tara N. Sainath, Arun Narayanan, 2017, INTERSPEECH.

Improving CTC Using Stimulated Learning for Sequence Modeling

Bo Li, Khe Chai Sim, Jahn Heymann, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

CONSENSUSNETWORK DECODING FOR STATISTICALMACHINE TRANSLATION SYSTEMCOMBINATION

Khe Chai Sim, Wj . Byrne, M J. FGales, 2007 .

Hidden logistic linear regression for support vector machine based phone verification

Khe Chai Sim, Bo Li, 2010, INTERSPEECH.

Learning factorized feature transforms for speaker normalization

Khe Chai Sim, Lahiru Samarakoon, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

Fusion of contrastive acoustic models for parallel phonotactic spoken language identification

Haizhou Li, Khe Chai Sim, 2007, INTERSPEECH.

The I4U system in NIST 2008 speaker recognition evaluation

Rong Tong, Bin Ma, Haizhou Li, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

Second order vector taylor series based robust speech recognition

Khe Chai Sim, Kai Yu, Yanmin Qian, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Entropy-based pruning of hidden units to reduce DNN parameters

Khe Chai Sim, Gautam Mantena, 2016, 2016 IEEE Spoken Language Technology Workshop (SLT).

Refinements of regression-based context-dependent modelling of deep neural networks for automatic speech recognition

Guangsen Wang, Khe Chai Sim, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Minimum Phone Error Training of

Mark J. F. Gales, Khe Chai Sim, M. Gales, 2006 .

Improving Speech Transcription for Mandarin-English Translation

Mark J. F. Gales, Marcus Tomalin, Lan Wang, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

A Beam-Search Decoder for Disfluency Detection

Hwee Tou Ng, Khe Chai Sim, Xuancong Wang, 2014, COLING.

Discriminative Product-of-Expert acoustic mapping for cross-lingual phone recognition

Khe Chai Sim, K. Sim, 2009, 2009 IEEE Workshop on Automatic Speech Recognition & Understanding.

A Spectral Masking Approach to Noise-Robust Speech Recognition Using Deep Neural Networks

Khe Chai Sim, Bo Li, 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Stimulated Deep Neural Network for Speech Recognition

Mark J. F. Gales, Khe Chai Sim, Panagiota Karanasou, 2016, INTERSPEECH.

learning Effective Factorized Hidden Layer Bases Using Student-Teacher Training for LSTM Acoustic Model Adaptation

Khe Chai Sim, Brian Kan-Wing Mak, Lahiru Samarakoon, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Probabilistic state clustering using conditional random field for context-dependent acoustic modelling

Khe Chai Sim, 2010, INTERSPEECH.

A Phone Verification Approach to Pronunciation Quality Assessment for Spoken Language Learning

Khe Chai Sim, 2009 .

Joint adaptation and adaptive training of TVWR for robust automatic speech recognition

Khe Chai Sim, Shilin Liu, 2014, INTERSPEECH.

Multi-stream temporally varying weight regression for cross-lingual speech recognition

Khe Chai Sim, Shilin Liu, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

Stream-based context-sensitive phone mapping for cross-lingual speech recognition

Haizhou Li, Khe Chai Sim, 2009, INTERSPEECH.

Improving the interpretability of deep neural networks with stimulated learning

Mark J. F. Gales, Khe Chai Sim, Shawn Tan, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

Streaming End-to-end Speech Recognition for Mobile Devices

Tara N. Sainath, Ding Zhao, Ian McGraw, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Combining Punctuation and Disfluency Prediction: An Empirical Study

Hwee Tou Ng, Khe Chai Sim, Xuancong Wang, 2014, EMNLP.

Low-rank bases for factorized hidden layer adaptation of DNN acoustic models

Khe Chai Sim, Lahiru Samarakoon, K. Sim, 2016, 2016 IEEE Spoken Language Technology Workshop (SLT).

Context-sensitive probabilistic phone mapping model for cross-lingual speech recognition

Haizhou Li, Khe Chai Sim, 2008, INTERSPEECH.

Regression-Based Context-Dependent Modeling of Deep Neural Networks for Speech Recognition

Guangsen Wang, Khe Chai Sim, 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Comparison of Smoothing Techniques for Robust Context Dependent Acoustic Modelling in Hybrid NN/HMM Systems

Guangsen Wang, Khe Chai Sim, 2011, INTERSPEECH.

Design and implementation of the note-taking style haptic voice recognition for mobile devices

Khe Chai Sim, Seungwhan Moon, 2012, ICMI '12.

Adaptation of precision matrix models on large vocabulary continuous speech recognition

Mark J. F. Gales, Khe Chai Sim, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Development of the CU-HTK 2004 broadcast news transcription systems

Mark J. F. Gales, Ricky Ho Yin Chan, Khe Chai Sim, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Towards implicit complexity control using variable-depth deep neural networks for automatic speech recognition

Khe Chai Sim, Shawn Tan, K. Sim, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Statistical lattice-based spoken document retrieval

Hwee Tou Ng, Haizhou Li, Khe Chai Sim, 2010, TOIS.

Factorized Hidden Layer Adaptation for Deep Neural Network Based Acoustic Modeling

Khe Chai Sim, Lahiru Samarakoon, K. Sim, 2016, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Discriminative semi-parametric trajectory model for speech recognition

Mark J. F. Gales, Khe Chai Sim, M. Gales, 2007, Comput. Speech Lang..

Adaptation of Deep Neural Network Acoustic Models for Robust Automatic Speech Recognition

Souvik Kundu, Khe Chai Sim, Yanmin Qian, 2017, New Era for Robust Speech Recognition, Exploiting Deep Learning.

An investigation of augmenting speaker representations to improve speaker normalisation for DNN-based speech recognition

Khe Chai Sim, Hengguan Huang, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A lattice-based approach to query-by-example spoken document retrieval

Hwee Tou Ng, Haizhou Li, Khe Chai Sim, 2008, SIGIR '08.

Multi-Attribute Factorized Hidden Layer Adaptation for DNN Acoustic Models

Khe Chai Sim, Lahiru Samarakoon, 2016, INTERSPEECH.

An investigation of temporally varying weight regression for noise robust speech recognition

Khe Chai Sim, Shilin Liu, 2013, INTERSPEECH.

Improving phone verification using state-level posterior features and support vector machine for automatic mispronunciation detection

Khe Chai Sim, 2009, SLaTE.

NIST 2007 Language Recognition Evaluation: From the Perspective of IIR

Rong Tong, Bin Ma, Haizhou Li, 2008, PACLIC.

Basis superposition precision matrix modelling for large vocabulary continuous speech recognition

Mark J. F. Gales, Khe Chai Sim, M. Gales, 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

A Weighted Combination of Speech with Text-based Models for Arabic Diacritization

Khe Chai Sim, Xiaoxuan Wang, Aisha S. Azim, 2012, INTERSPEECH.

Learning utterance-level normalisation using Variational Autoencoders for robust automatic speech recognition

Khe Chai Sim, Shawn Tan, 2016, 2016 IEEE Spoken Language Technology Workshop (SLT).

Integrating conditional random fields and joint multi-gram model with syllabic features for grapheme-to-phone conversion

Khe Chai Sim, Xiaoxuan Wang, 2013, INTERSPEECH.

INVITED PAPER Special Section on Recent Advances in Machine Learning for Spoken Language Processing Sensitivity-Characterised Activity Neurogram ( SCAN ) for Visualising and Understanding the Inner Workings of Deep Neural Network

Khe Chai Sim, 2016 .

Incorporating a Generative Front-End Layer to Deep Neural Network for Noise Robust Automatic Speech Recognition

Mark J. F. Gales, Souvik Kundu, Khe Chai Sim, 2016, INTERSPEECH.

MOGAT: mobile games with auditory training for children with cochlear implants

Ye Wang, Khe Chai Sim, Yinsheng Zhou, 2012, ACM Multimedia.

Word level automatic alignment of music and lyrics using vocal synthesis

Haizhou Li, Khe Chai Sim, Namunu Chinthaka Maddage, 2010, ACM Trans. Multim. Comput. Commun. Appl..

Robust phone set mapping using decision tree clustering for cross-lingual phone recognition

Haizhou Li, Khe Chai Sim, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

A Trajectory-based Parallel Model Combination with a unified static and dynamic parameter compensation for noisy speech recognition

Khe Chai Sim, Minh-Thang Luong, Minh-Thang Luong, 2011, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding.

Minimum phone error training of precision matrix models

Mark J. F. Gales, Khe Chai Sim, M. Gales, 2006, IEEE Transactions on Audio, Speech, and Language Processing.

An ideal hidden-activation mask for deep neural networks based noise-robust speech recognition

Khe Chai Sim, Bo Li, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Consensus Network Decoding for Statistical Machine Translation System Combination

Hichem Sahbi, William J. Byrne, Mark J. F. Gales, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Probabilistic Integration of Partial Lexical Information for Noise Robust Haptic Voice Recognition

Khe Chai Sim, 2012, ACL.

Domain Adaptation Using Factorized Hidden Layer for Robust Automatic Speech Recognition

Tara N. Sainath, Arun Narayanan, Khe Chai Sim, 2018, INTERSPEECH.

Precision matrix modelling for large vocabulary continuous speech recognition

Khe Chai Sim, Mark J. F. Gales, M. Gales, 2004 .

On combining i-vectors and discriminative adaptation methods for unsupervised speaker normalization in DNN acoustic models

Khe Chai Sim, Lahiru Samarakoon, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multi-Dialect Speech Recognition with a Single Sequence-to-Sequence Model

Tara N. Sainath, Patrick Nguyen, Zhifeng Chen, 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Microphone Distance Adaptation Using Cluster Adaptive Training for Robust Far Field Speech Recognition

Khe Chai Sim, Animesh Prasad, 2016, INTERSPEECH.

Semantic Transliteration of Personal Names

Haizhou Li, Khe Chai Sim, Jin-Shea Kuo, 2007, ACL.

Dynamic Conditional Random Fields for Joint Sentence Boundary and Punctuation Prediction

Hwee Tou Ng, Khe Chai Sim, Xuancong Wang, 2012, INTERSPEECH.

Context-dependent modelling of deep neural network using logistic regression

Guangsen Wang, Khe Chai Sim, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

Context dependent acoustic keyword spotting using deep neural network

Guangsen Wang, Khe Chai Sim, 2013, 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference.

Comparison of discriminative input and output transformations for speaker adaptation in the hybrid NN/HMM systems

Khe Chai Sim, Bo Li, Bo Li, 2010, INTERSPEECH.

A multimodal stroke-based predictive input for efficient Chinese text entry on mobile devices

Khe Chai Sim, 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

An investigation of spectral restoration algorithms for deep neural networks based noise robust speech recognition

Yu Tsao, Khe Chai Sim, Bo Li, 2013, INTERSPEECH.

Discrete expected likelihood kernel for SVM-based speaker verification

Haizhou Li, Kong-Aik Lee, Tomi Kinnunen, 2010, 2010 18th European Signal Processing Conference.

Temporally Varying Weight Regression: A Semi-Parametric Trajectory Model for Automatic Speech Recognition

Khe Chai Sim, Shilin Liu, K. Sim, 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Query-by-Example Spoken Document Retrieval : The Star Challenge 2008

Haizhou Li, Kin Mun Lye, Vivek Singh, 2009 .

The NUS sung and spoken lyrics corpus: A quantitative comparison of singing and speech

Ye Wang, Khe Chai Sim, Bo Li, 2013, 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference.

Sensitivity-Characterised Activity Neurogram (SCAN) for Visualising and Understanding the Inner Workings of Deep Neural Network

Khe Chai Sim, 2016, IEICE Trans. Inf. Syst..

Adaptive score fusion using Weighted Logistic Linear Regression for spoken language recognition

Kong-Aik Lee, Khe Chai Sim, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Improving Interpretability and Regularization in Deep Learning

Mark J. F. Gales, Anton Ragni, Khe Chai Sim, 2018, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Temporally varying model parameters for large vocabulary continuous speech recognition

Mark J. F. Gales, Khe Chai Sim, M. Gales, 2005, INTERSPEECH.

Semi-parametric trajectory modelling using temporally varying feature mapping for speech recognition

Khe Chai Sim, Shilin Liu, 2010, INTERSPEECH.

Sequential Classification Criteria for NNs in Automatic Speech Recognition

Guangsen Wang, Khe Chai Sim, K. Sim, 2011, INTERSPEECH.

Speaker-aware training of LSTM-RNNS for acoustic modelling

Souvik Kundu, Yu Zhang, Khe Chai Sim, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Parameter clustering for temporally varying weight regression for automatic speech recognition

Khe Chai Sim, Shilin Liu, 2013, INTERSPEECH.

Approximated Parallel Model Combination for efficient noise-robust speech recognition

Khe Chai Sim, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Joint acoustic factor learning for robust deep neural network based automatic speech recognition

Marc Delcroix, Souvik Kundu, Khe Chai Sim, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Subspace LHUC for Fast Adaptation of Deep Neural Network Acoustic Models

Khe Chai Sim, Lahiru Samarakoon, K. Sim, 2016, INTERSPEECH.

Noise adaptive front-end normalization based on Vector Taylor Series for Deep Neural Networks in robust speech recognition

Khe Chai Sim, Bo Li, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Investigation of acoustic modeling techniques for LVCSR systems

Mark J. F. Gales, Xunying Liu, Khe Chai Sim, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Toward Domain-Invariant Speech Recognition via Large Scale Training

Arun Narayanan, Khe Chai Sim, Michiel Bacchiani, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

Efficient Implementation of Recurrent Neural Network Transducer in Tensorflow

Khe Chai Sim, Tom Bagby, Kanishka Rao, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

On combining DNN and GMM with unsupervised speaker adaptation for robust automatic speech recognition

Khe Chai Sim, Shilin Liu, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Understanding Recurrent Neural State Using Memory Signatures

Khe Chai Sim, Kean K. Chin, Skanda Koppula, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Haptic Voice Recognition: Augmenting speech modality with touch events for efficient speech recognition

Khe Chai Sim, 2010, 2010 IEEE Spoken Language Technology Workshop.

Improving robustness of deep neural networks via spectral masking for automatic speech recognition

Khe Chai Sim, Bo Li, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

A minimum variance asynchronous Detection Error Trade-off performance analysis for multi-class detection problems

Khe Chai Sim, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Development of the 2004 CU-HTK English CTS systems using more than two thousand hours of data

Xunying Liu, Khe Chai Sim, Gunnar Evermann, 2004 .

Improving mandarin predictive text input by augmenting pinyin initials with speech and tonal information

Guangsen Wang, Khe Chai Sim, Xiaoxuan Wang, 2012, ICMI '12.

Development of the CUHTK 2004 Mandarin conversational telephone speech transcription system

Mark J. F. Gales, Xunying Liu, Khe Chai Sim, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Implicit trajectory modelling using temporally varying weight regression for automatic speech recognition

Khe Chai Sim, Shilin Liu, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

An investigation into learning effective speaker subspaces for robust unsupervised DNN adaptation

Khe Chai Sim, Brian Kan-Wing Mak, Lahiru Samarakoon, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

An Investigation Into On-device Personalization of End-to-end Automatic Speech Recognition Models

Khe Chai Sim, Franccoise Beaufays, Petr Zadrazil, 2019, INTERSPEECH.

ICMI'12 grand challenge: haptic voice recognition

Hank Liao, Shengdong Zhao, Khe Chai Sim, 2012, ICMI '12.

Low-Rank Gradient Approximation for Memory-Efficient on-Device Training of Deep Neural Network

Giovanni Motta, Khe Chai Sim, Franccoise Beaufays, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

The Cu-Htk Mandarin Broadcast News Transcription System

Mark J. F. Gales, Xunying Liu, Khe Chai Sim, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

Modeling long temporal contexts for robust DNN-based speech recognition

Khe Chai Sim, Bo Li, 2014, INTERSPEECH.

On constructing and analysing an interpretable brain model for the DNN based on hidden activity patterns

Khe Chai Sim, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

Speak-as-you-swipe (SAYS): a multimodal interface combining speech and gesture keyboard synchronously for continuous mobile text entry

Khe Chai Sim, 2012, ICMI '12.

Personalization of End-to-End Speech Recognition on Mobile Devices for Named Entities

Giovanni Motta, Khe Chai Sim, Harry Zhang, 2019, 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

A Two-stage Speaker Adaptation Approach for Subspace Gaussian Mixture Model based Nonnative Speech Recognition

Khe Chai Sim, Bo Li, 2012, INTERSPEECH.

Incremental Layer-wise Self-Supervised Learning for Efficient Speech Domain Adaptation On Device pdf

Khe Chai Sim, Zhouyuan Huo, Ananya Misra, 2021, ArXiv.

Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition pdf

Khe Chai Sim, Tsendsuren Munkhdalai, Trevor Strohman, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition pdf

Tara N. Sainath, Bhuvana Ramabhadran, Aren Jansen, 2021, ArXiv.

On-Device Personalization of Automatic Speech Recognition Models for Disordered Speech pdf

Khe Chai Sim, Franccoise Beaufays, Julie Cattiau, 2021, ArXiv.

A Comparison of Supervised and Unsupervised Pre-Training of End-to-End Models

Arun Narayanan, Khe Chai Sim, Zhouyuan Huo, 2021, Interspeech.

Large-Scale ASR Domain Adaptation Using Self- and Semi-Supervised Learning pdf

Khe Chai Sim, Zhouyuan Huo, Ananya Misra, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Joint Unsupervised and Supervised Training for Multilingual ASR pdf

Tara N. Sainath, Ankur Bapna, Khe Chai Sim, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Robust Continuous On-Device Personalization for Automatic Speech Recognition

Khe Chai Sim, Tsendsuren Munkhdalai, Françoise Beaufays, 2021, Interspeech.

Recent developments at Cambridge in broadcast news transcription

Mark J. F. Gales, Khe Chai Sim, Gunnar Evermann, 2004 .