Tom Ko

发表

Eigentriphones: A basis for context-dependent acoustic modeling

Brian Kan-Wing Mak, Tom Ko, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Eigentrigraphemes for under-resourced languages

Brian Kan-Wing Mak, Tom Ko, 2014, Speech Commun..

Problems of modeling phone deletion in conversational speech for speech recognition

Brian Kan-Wing Mak, Tom Ko, 2010, 2010 7th International Symposium on Chinese Spoken Language Processing.

Automatic estimation of decoding parameters using large-margin iterative linear programming

Brian Kan-Wing Mak, Tom Ko, 2009, INTERSPEECH.

JHU ASpIRE system: Robust LVCSR with TDNNS, iVector adaptation and RNN-LMS

Sanjeev Khudanpur, Daniel Povey, Tom Ko, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

Eigentriphones for Context-Dependent Acoustic Modeling

Brian Kan-Wing Mak, Tom Ko, 2013, IEEE Transactions on Audio, Speech, and Language Processing.

Modeling inter-cluster and intra-cluster discrimination among triphones

Brian Kan-Wing Mak, Dongpeng Chen, Tom Ko, 2014, The 9th International Symposium on Chinese Spoken Language Processing.

An empirical exploration of CTC acoustic models

Florian Metze, Alexander H. Waibel, Yajie Miao, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Subspace Gaussian mixture model with state-dependent subspace dimensions

Cheung-Chi Leung, Brian Kan-Wing Mak, Tom Ko, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification

Daniel Povey, David Snyder, Brian Kan-Wing Mak, 2018, INTERSPEECH.

AutoSpeech 2020: The Second Automated Machine Learning Challenge for Speech Classification

Wei-Wei Tu, Tom Ko, Zhen Xu, 2020, INTERSPEECH.

MetaMix: Improved Meta-Learning with Interpolation-based Consistency Regularization pdf

Qing Li, Jianping Wang, Yun Ma, 2020, ArXiv.

Improving speech recognition by explicit modeling of phone deletions

Brian Kan-Wing Mak, Tom Ko, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Audio augmentation for speech recognition

Sanjeev Khudanpur, Daniel Povey, Tom Ko, 2015, INTERSPEECH.

A study on data augmentation of reverberant speech for robust speech recognition

Sanjeev Khudanpur, Daniel Povey, Tom Ko, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

An Investigation of Few-Shot Learning in Spoken Term Classification

Qing Li, Xiao Chen, Xin Jiang, 2020, INTERSPEECH.

Mixup Learning Strategies for Text-Independent Speaker Verification

Yingke Zhu, Tom Ko, Brian Mak, 2019, INTERSPEECH.

Derivation of eigentriphones by weighted principal component analysis

Brian Kan-Wing Mak, Tom Ko, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Long Distance Voice Channel Diagnosis Using Deep Neural Networks

Zhen Qin, Guangjian Tian, Tom Ko, 2018, INTERSPEECH.

Min-max discriminative training of decoding parameters using iterative linear programming

Brian Kan-Wing Mak, Tom Ko, 2008, INTERSPEECH.

A Fully Automated Derivation of State-Based Eigentriphones for Triphone Modeling with No Tied States Using Regularization

Brian Kan-Wing Mak, Tom Ko, 2011, INTERSPEECH.

Meta Learning for Few-shot Keyword Spotting pdf

Xiao Chen, Xin Jiang, Qing Li, 2018, ArXiv.

Prototypical Networks for Small Footprint Text-Independent Speaker Verification

Qing Li, Tom Ko, Yangbin Chen, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multi-View Self-Attention Based Transformer for Speaker Recognition pdf

Zhihua Wei, Tom Ko, Yu Zhang, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Meta-Learning Approach for User-Defined Spoken Term Classification with Varying Classes and Examples

Jianping Wang, Tom Ko, Yangbin Chen, 2021, Interspeech 2021.

Improving Attention-based End-to-end ASR by Incorporating an N-gram Neural Network

Tom Ko, Junyi Ao, Tom Ko, 2021, 2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP).

MetaMix: Improved Meta-Learning with Interpolation-based Consistency Regularization

Tom Ko, Yangbin Chen, Qing Li, 2020, 2020 25th International Conference on Pattern Recognition (ICPR).

Token-Level Supervised Contrastive Learning for Punctuation Restoration pdf

Tom Ko, Bo Wu, Qiushi Huang, 2021, Interspeech 2021.

Exploring Machine Speech Chain for Domain Adaptation and Few-Shot Speaker Adaptation pdf

Tom Ko, Lei He, Yan Deng, 2021, ArXiv.

Auto-KWS 2021 Challenge: Task, Datasets, and Baselines pdf

Lei Xie, Hung-yi Lee, Wei-Wei Tu, 2021, Interspeech.

An Investigation of Positional Encoding in Transformer-based End-to-end Speech Recognition

Tom Ko, Fengpeng Yue, Fengpeng Yue, 2021, 2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP).

CL4AC: A Contrastive Loss for Audio Captioning pdf

Mark D. Plumbley, Wenwu Wang, Tom Ko, 2021, ArXiv.

An Encoder-Decoder Based Audio Captioning System with Transfer and Reinforcement Learning pdf

Wenwu Wang, Tom Ko, Jinzheng Zhao, 2021, DCASE.

SpeechT5: Unified-Modal Encoder-Decoder Pre-training for Spoken Language Processing pdf

Furu Wei, Zhihua Wei, Jinyu Li, 2021, ArXiv.