Follow
Tom Ko
Tom Ko
ByteDance AI Lab Hong Kong
Verified email at bytedance.com - Homepage
Title
Cited by
Cited by
Year
Audio augmentation for speech recognition
T Ko, V Peddinti, D Povey, S Khudanpur
Sixteenth annual conference of the international speech communication …, 2015
8542015
A study on data augmentation of reverberant speech for robust speech recognition
T Ko, V Peddinti, D Povey, ML Seltzer, S Khudanpur
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
5292017
Self-attentive speaker embeddings for text-independent speaker verification.
Y Zhu, T Ko, D Snyder, B Mak, D Povey
Interspeech 2018, 3573-3577, 2018
2062018
Jhu aspire system: Robust lvcsr with tdnns, ivector adaptation and rnn-lms
V Peddinti, G Chen, V Manohar, T Ko, D Povey, S Khudanpur
2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU …, 2015
1102015
An empirical exploration of CTC acoustic models
Y Miao, M Gowayyed, X Na, T Ko, F Metze, A Waibel
2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016
842016
Mixup Learning Strategies for Text-Independent Speaker Verification.
Y Zhu, T Ko, B Mak
Interspeech, 4345-4349, 2019
192019
An investigation of few-shot learning in spoken term classification
Y Chen, T Ko, L Shang, X Chen, X Jiang, Q Li
arXiv preprint arXiv:1812.10233, 2018
17*2018
Speecht5: Unified-modal encoder-decoder pre-training for spoken language processing
J Ao, R Wang, L Zhou, S Liu, S Ren, Y Wu, T Ko, Q Li, Y Zhang, Z Wei, ...
arXiv preprint arXiv:2110.07205, 2021
132021
Eigentrigraphemes for under-resourced languages
T Ko, B Mak
Speech Communication 56, 132-141, 2014
132014
A fully automated derivation of state-based eigentriphones for triphone modeling with no tied states using regularization
T Ko, B Mak
Twelfth Annual Conference of the International Speech Communication Association, 2011
132011
Eigentriphones: A basis for context-dependent acoustic modeling
T Ko, B Mak
2011 IEEE International Conference on Acoustics, Speech and Signal …, 2011
122011
An encoder-decoder based audio captioning system with transfer and reinforcement learning
X Mei, Q Huang, X Liu, G Chen, J Wu, Y Wu, J Zhao, S Li, T Ko, HL Tang, ...
arXiv preprint arXiv:2108.02752, 2021
112021
Prototypical networks for small footprint text-independent speaker verification
T Ko, Y Chen, Q Li
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
112020
CL4AC: A contrastive loss for audio captioning
X Liu, Q Huang, X Mei, T Ko, HL Tang, MD Plumbley, W Wang
arXiv preprint arXiv:2107.09990, 2021
102021
Eigentriphones for context-dependent acoustic modeling
T Ko, B Mak
IEEE Transactions on Audio, Speech, and Language Processing 21 (6), 1285-1294, 2013
102013
Automatic estimation of decoding parameters using large-margin iterative linear programming
B Mak, T Ko
Tenth Annual Conference of the International Speech Communication Association, 2009
102009
An encoder-decoder based audio captioning system with transfer and reinforcement learning for DCASE challenge 2021 task 6
X Mei, Q Huang, X Liu, G Chen, J Wu, Y Wu, J Zhao, S Li, T Ko, HL Tang, ...
DCASE2021 Challenge, Tech. Rep, 2021
82021
Min-max discriminative training of decoding parameters using iterative linear programming
B Mak, T Ko
Ninth Annual Conference of the International Speech Communication Association, 2008
72008
Derivation of eigentriphones by weighted principal component analysis
T Ko, B Mak
2012 IEEE International Conference on Acoustics, Speech and Signal …, 2012
62012
Token-level supervised contrastive learning for punctuation restoration
Q Huang, T Ko, HL Tang, X Liu, B Wu
arXiv preprint arXiv:2107.09099, 2021
52021
The system can't perform the operation now. Try again later.
Articles 1–20