Faculty

KO, Tom
Assistant Professor
Assistant Professor
kot_AT_sustech.edu.cn

Research Area:

Speech recognition, Speaker verification, Natural language processing

Educational Background

◆ 2010-2014,Ph.D in Computer Science and Engineering, The Hong Kong University of Science and Technology

◆ 2007-2010,M.Phil in Computer Science and Engineering, The Hong Kong University of Science and Technology

◆ 2000-2003,B.Sc. degree in Computer Engineering, The Chinese University of Hong Kong

Professional Experience

◆ 2014-2018, Huawei Noah's Ark Lab in Hong Kong

Honors & Awards

◆ 2nd best presentation in Signal Processing Postgraduate Forum 2010 organized by the IEEE Hong Kong Chapter

◆ Professor Samuel Chanson Best Teaching Assistant Award 2011-12

Selected Publication

1. Yingke Zhu, Tom Ko, David Snyder, Brian Mak, Daniel Povey "Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification", in Proceedings of Interspeech, September, 2018, Hyderabad, India

2. Tom Ko, Vijayaditya Peddinti, Daniel Povey, Michael L. Seltzer, Sanjeev Khudanpur "A study on data augmentation of reverberant speech for robust speech recognition", in Proceedings of ICASSP, March, 2017, New Orleans, USA

3. Yajie Miao, Mohammad Gowayyed, Xingyu Na, Tom Ko, Florian Metze, and Alexander Waibel "An Empirical Exploration of CTC Acoustic Models", in Proceedings of ICASSP, March, 2016, Shanghai, China

4. Tom Ko, Vijayaditya Peddinti, Daniel Povey, Sanjeev Khudanpur " Audio Augmentation for Speech Recognition", in Proceedings of Interspeech, September, 2015, Dresden, Germany

5. Tom Ko and Brian Mak, "Eigentrigraphemes for Under-Resourced Languages", Speech Communications, volume 56, pages 132-141, January, 2014

6. Tom Ko and Brian Mak, "Eigentriphones for Context-dependent Acoustic Modeling", IEEE Transactions on Audio, Speech and Language Processing, volume 21, number 6, pages 1285-1294, 2013