image

Current Research Students


Name MPhil/PhD/RA Exp. Grad Date Thesis Topic
NIU Zhe PhD 2024/08 sign-language recognition, lip2wav
ZUO Ronglai PhD 2024/08 sign-language recognition, translation and generation



Former Research Students/Postdocs


Name Degree Grad Date Whereabout Thesis Title
20. HUANG Chun Fung Ranzo MPhil 2023/08 Infotalk, Hong Kong, 2024 Low-Resource Speech Recognition Using Pre-trained Speech Representation Models
19. ZHU Yingke PhD 2022/09 Fano Lab, Hong Kong Deep speaker Representation Learning in Speaker Verification
18. Wei LI MPhil 2022/05 Multilingual Document Embedding with Sequential Neural Network Models
17. Raymond CHUNG MPhil 2022/01 LSCM, Hong Kong Speech Imitation by Neural Speech Synthesis with On-the-Fly Data Augmentation
16. YU Xinyuan MPhil 2020/08 NetEase, Guangzhou, China, 2020 Non-parallel Many-to-many Voice Conversion by Knowledge Transfer from a Pre-trained Text-to-speech Model
15. LIU Zhaoyu MPhil 2020/04 Baidu, Beijing, China, 2020 Multi-lingual and Multi-speaker Neural Text-to-speech System
14. FUNG Ho Long MPhil 2018/12 Fano Lab, Hong Kong Practical Improvements to Automatic Visual Speech Recognition
13. HUANG Hengguan MPhil 2018/11 Recurrent Poisson Process Unit for Automatic Speech Recognition
12. Lahiru SAMARAKOON Postdoc 2017/12 Fano Lab, Hong Kong Adaptation of DNN-based Acoustic Models
11. CHEN Dong Peng PhD 2015/08 Own Startup, VoiceAI, China ASR Using Multi-tasking Learning Deep Neural Network
10. KO Yu Ting, Tom PhD
MPhil
2014/04
2010/08
ByteDance, China, 2024 Distinct Triphone Modeling for Automatic Speech Recognition
Phone Deletion Modeling in Speech Recognition
9. YE Guo Li PhD 2013/01 Microsoft, Redmond, USA The Use of Discrete Distributions with a Very Large Codebook for Automatic Speech Recognition and Speaker Verification
8. NG Yik Lun, Benny MPhil 2008/01 Discriminative Training of Stream Weights in a Multi-Stream Classifier as a Linear Programming Problem
7. HSIAO Wend Huu, Roger MPhil 2004/11 Apple, Boston, USA Kernel Eigenspace-based MLLR Adaptation
6. HO Ka Lun, Simon MPhil 2003/8 HSBC, Hong Kong Kernel Eigenvoice Speaker Adaptation
5. CHAN Kin Wah, Ivan MPhil 2003/5 Pruning Hidden Markov Model with Optimal Brain Surgeon
4. CHONG Fong Ho, Franco MPhil 2003/1 Frequency Stream Tying Hidden Markov Model
3. WANG Chi Yung MPhil 2002/12 Knowledge-based Sense Pruning using the HowNet: an Alternative to Word Sense Disambiguation
2. TAM Yik Cheung, Wilson MPhil 2001/7 NYU Shanghai, 2021; WeChat, China, 2017 The Development of an Asynchronous Multi-Band Automatic Speech Recognition System
1. WONG Kwok Man MPhil 2000/8 Speaker Adaptation with Subspace Regression Classes



Current and Former Visiting Interns


Name Home University UG/PG Period
5. Renzhi DUAN Tsinghua University, China UG 2016 Summer
4. Aaron Nicolson Griffith University, Australia UG 2016 Spring
3. Chenwei XIE Zhejiang University, China UG 2014 Fall
2. Daniel R. van Niekerk North-West University, S. Africa PG 2011 Summer
1. Chien-Lin HUANG National Cheng Kung University PG 2007 Fall