Chao Zhang

Chao Zhang 

Chao Zhang CN (Chinese: 张超)
Research Associate (
CV)
Machine Intelligence Laboratory
Cambridge University Engineering Department
University of Cambridge

Education Background

Selected Publications

Thesis

  1. Joint Training Methods for Tandem and Hybrid Speech Recognition Systems using Deep Neural Networks
    C. Zhang
    Ph.D. Thesis, University of Cambridge, 2017

  1. Accented Chinese Speech Recognition Based on Speech Attributes
    C. Zhang
    M.Sc. Thesis, Tsinghua University, 2012

Journal Papers

  1. Relating dynamic brain states to dynamic machine states: Human and machine solutions to the speech recognition problem
    C. Wingfield, L. Su, X. Liu, C. Zhang, P.C. Woodland, A. Thwaites, E. Fonteneau, W.D. Marslen-Wilson
    PLOS Computational Biology, vol. 13, no. 9, pp. 1-25, September 2017

  2. Reliable Accent Specific Unit Generation with Discriminative Dynamic Gaussian Mixture Selection for Multi-accent Chinese Speech Recognition
    C. Zhang, Y. Liu, Y. Xia, X. Wang, C.-H. Lee
    IEEE Transactions on Audio, Speech, and Language Processing (TASLP), vol. 21, no. 10, pp. 2073-2084, October 2013

  3. Acoustic Model Reconstruction for Multi-accent Chinese Speech Recognition (in Chinese)
    C. Zhang, Y. Liu, T.F. Zheng
    Journal of Tsinghua University (Science & Technology), Vol. 51, no. 9, pp. 1161-1166, September 2011
    NCMMSC 2011 Best Student Paper Award

Conference Papers

  1. High Order Recurrent Neural Networks for Acoustic Modelling [poster]
    C. Zhang and P.C. Woodland
    IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP), Calgary, Alberta, Canada, April 15-21, 2018

  2. Improved TDNNs using Deep Kernels and Frequency Dependent Grid-RNNs
    F.L. Kreyssig, C. Zhang, and P.C. Woodland
    IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP), Calgary, Alberta, Canada, April 15-21, 2018

  3. Joint Optimisation of Tandem Systems using Gaussian Mixture Density Neural Network Discriminative Sequence Training [slides]
    C. Zhang and P.C. Woodland
    IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP), New Orleans, Louisiana, USA, March 5-9, 2017

  4. Selection of Multi-Genre Broadcast Data for the Training of Automatic Speech Recognition Systems
    P. Lanchantin, M.J.F. Gales, P. Karanasou, X. Liu, Y. Qian, L. Wang, P.C. Woodland, and C. Zhang
    ISCA Interspeech 2016, San Francisco, California, USA, September 8-12, 2016, pp. 3057-3061

  5. DNN Speaker Adaptation using Parameterised Sigmoid and ReLU Hidden Activation Functions [slides] [poster]
    C. Zhang and P.C. Woodland
    IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP), Shanghai, China, March 20-25, 2016, pp. 5300-5304

  6. System Combination with Log-linear Models
    J. Yang, C. Zhang, A. Ragni, M.J.F. Gales, and P.C. Woodland
    IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP), Shanghai, China, March 20-25, 2016, pp. 5675-5679

  7. Improved DNN-based Segmentation for Multi-genre Broadcast Audio
    L. Wang, C. Zhang, P.C. Woodland, M.J.F. Gales, P. Karanasou, P. Lanchantin, X. Liu, Y. Qian
    IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP), Shanghai, China, March 20-25, 2016, pp. 5700-5704

  8. Cambridge University Transcription Systems for the Multi-genre Broadcast Challenge
    P.C. Woodland, X. Liu, Y. Qian, C. Zhang, M.J.F. Gales, P. Karanasou, P. Lanchantin, and L. Wang
    IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Scottsdale, Arizona, USA, December 13-17, 2015, pp. 639-646

  9. The Development of the Cambridge University Alignment Systems for the Multi-genre Broadcast Challenge
    P. Lanchantin, M.J.F. Gales, P. Karanasou, X. Liu, Y. Qian, L. Wang, P.C. Woodland, and C. Zhang
    IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Scottsdale, Arizona, USA, December 13-17, 2015, pp. 647-653

  10. Speaker Diarisation and Longitudinal Linking in Multi-genre Broadcast Data
    P. Karanasou, M.J.F. Gales, P. Lanchantin, X. Liu, Y. Qian, L. Wang, P.C. Woodland, and C. Zhang
    IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Scottsdale, Arizona, USA, December 13-17, 2015, pp. 660-666

  11. Structured Discriminative Models using Deep Neural-Network Features
    R.C. van Dalen, J. Yang, H. Wang, A. Ragni, C. Zhang, and M.J.F. Gales
    IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Scottsdale, Arizona, USA, December 13-17, 2015, pp. 160-166

  12. The Cambridge University 2014 BOLT Conversational Telephone Mandarin Chinese LVCSR System for Speech Translation
    X. Liu, F. Flego, L. Wang, C. Zhang, M.J.F. Gales, and P.C. Woodland
    ISCA Interspeech 2015, Dresden, Germany, September 6-10, 2015, pp. 3145-3149

  13. Parameterised Sigmoid and ReLU Hidden Activation Functions for DNN Acoustic Modelling [slides] [poster]
    C. Zhang and P.C. Woodland
    ISCA Interspeech 2015, Dresden, Germany, September 6-10, 2015, pp. 3224-3228

  14. A General Artificial Neural Network Extension for HTK [slides] [poster]
    C. Zhang and P.C. Woodland
    ISCA Interspeech 2015, Dresden, Germany, September 6-10, 2015, pp. 3581-3585

  15. Joint Decoding of Tandem and Hybrid Systems for Improved Keyword Spotting on Low Resource Languages
    H. Wang, A. Ragni, M.J.F. Gales, K.M. Knill, P.C. Woodland, and C. Zhang
    ISCA Interspeech 2015, Dresden, Germany, September 6-10, 2015, pp. 3660-3664

  16. Standalone Training of Context-dependent Deep Neural Network Acoustic Models [slides] [poster]
    C. Zhang and P.C. Woodland
    IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP), Florence, Italy, May 4-9, 2014, pp. 5597-5601
    IBM Research Spoken Language Processing Paper Award

  17. Investigation of Multilingual Deep Neural Networks for Spoken Term Detection
    K.M. Knill, M.J.F. Gales, S.P. Rath, P.C. Woodland, C. Zhang, and S. Zhang
    IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Olomouc, Czech Republic, December 8-12, 2013, pp. 138-143

  18. Discriminative Dynamic Gaussian Mixture Selection with Enhanced Robustness and Performance for Multi-accent Speech Recognition [slides]
    C. Zhang, Y. Liu, Y. Xia, and C.-H. Lee
    IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP), Kyoto, Japan, March 25-30, 2012, pp. 4749-4752

  19. Detection-based Accented Speech Recognition using Articulatory Features [slides]
    C. Zhang, Y. Liu, and C.-H. Lee
    IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Hawaii, USA, December 11-15, 2011, pp. 500-505
    Panel Member Paper Award

  20. Reliable Accent Specific Unit Generation with Dynamic Gaussian Mixture Selection for Multi-accent Speech Recognition
    C. Zhang, Y. Liu, Y. Xia, T.F. Zheng, J. Olsen, and J. Tian
    IEEE International Conference on Multimedia & Expo (ICME), Barcelona, Spain, July 11-15, 2011, pp. 1-6
    Top 15% Rated Paper

  21. Asymmetric Acoustic Model for Accented Speech Recognition
    C. Zhang, Y. Liu, and T.F. Zheng
    Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Xian, China, October 18-21, 2011, pp. 919-923

  22. An in-car Chinese Noise Database for Speech Recognition
    J. Hou, Y. Liu, C. Zhang, and S. Huang
    International Conference on Asian Language Processing (IALP), Penang, Malaysia, November 15-17, 2011, pp. 228-231

Research Experiences

Selected Services

Selected Presentations

Contact Information

Room BE5-02, Baker Building
Trumpington Street, Cambridge, CB2 1PZ, UK
Email: cz277EMAIL