Tom Ko
Tom Ko
Southern University of Science and Technology
Bestätigte E-Mail-Adresse bei sustech.edu.cn - Startseite
Titel
Zitiert von
Zitiert von
Jahr
Audio augmentation for speech recognition
T Ko, V Peddinti, D Povey, S Khudanpur
Sixteenth Annual Conference of the International Speech Communication …, 2015
6062015
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
3252017
Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification.
Y Zhu, T Ko, D Snyder, B Mak, D Povey
Interspeech 2018, 3573-3577, 2018
1442018
JHU ASpIRE system: Robust LVCSR with TDNNS, iVector adaptation and RNN-LMS.
V Peddinti, G Chen, V Manohar, T Ko, D Povey, S Khudanpur
ASRU, 539-546, 2015
842015
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
762016
Risk-constrained operation for Internet data centers in deregulated electricity markets
L Yu, T Jiang, Y Cao, Q Zhang
IEEE Transactions on Parallel and Distributed Systems 25 (5), 1306-1316, 2014
412014
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
Mixup Learning Strategies for Text-Independent Speaker Verification.
Y Zhu, T Ko, B Mak
Interspeech, 4345-4349, 2019
122019
Eigentriphones: A basis for context-dependent acoustic modeling
T Ko, B Mak
2011 IEEE International Conference on Acoustics, Speech and Signal …, 2011
122011
Eigentriphones for context-dependent acoustic modeling
T Ko, B Mak
IEEE Transactions on Audio, Speech, and Language Processing 21 (6), 1285-1294, 2013
112013
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
112009
Meta learning for few-shot keyword spotting
Y Chen, T Ko, L Shang, X Chen, X Jiang, Q Li
arXiv preprint arXiv:1812.10233, 2018
8*2018
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
82008
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
72020
Derivation of eigentriphones by weighted principal component analysis
T Ko, B Mak
2012 IEEE International Conference on Acoustics, Speech and Signal …, 2012
62012
Improving speech recognition by explicit modeling of phone deletions
T Ko, B Mak
2010 IEEE International Conference on Acoustics, Speech and Signal …, 2010
42010
AutoSpeech 2020: The Second Automated Machine Learning Challenge for Speech Classification
J Wang, T Ko, Z Xu, X Guo, S Liu, WW Tu, L Xie
arXiv preprint arXiv:2010.13130, 2020
22020
Exploring Machine Speech Chain for Domain Adaptation and Few-Shot Speaker Adaptation
F Yue, Y Deng, L He, T Ko
arXiv preprint arXiv:2104.03815, 2021
2021
Auto-KWS 2021 Challenge: Task, Datasets, and Baselines
J Wang, Y He, C Zhao, Q Shao, WW Tu, T Ko, H Lee, L Xie
arXiv preprint arXiv:2104.00513, 2021
2021
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20