---

Research Interests

• Structured Support Vector Machines for Speech Recognition (Toshiba funded project)
• Generative Kernels and Score-Spaces for Classification of Speech (EPSRC project)
• BABEL (IARPA project)

Journal Papers:

• S.-X. Zhang, and M.J.F. Gales (2012). “Structured SVMs for Automatic Speech Recognition.”
  In IEEE Trans. on Audio Speech and Language Processing 21(3), pp. 544-555. [BibTex]

• S.-X. Zhang, A. Ragni and M.J.F. Gales (2010). “Structured Log Linear Models for Noise Robust Speech Recognition.”
  In IEEE Signal Processing Letters 17 (11), pp. 945-948. [BibTex]

• S.-X. Zhang and M.W. Mak (2010), "Optimized Discriminative Kernel for SVM Scoring and its Application to Speaker Verification."
  In IEEE Trans. on Neural Networks 22 (2), pp. 173-185. [BibTex]

• S.-X. Zhang and M.W. Mak (2009), "A New Adaptation Approach to High-Level Speaker-Model Creation in Speaker Verification."
  In Speech Communication 51 (6), pp. 534-550. [BibTex]

• S.-X. Zhang, M.W. Mak and Helen M. Meng (2007), "Speaker Verification via High-Level Feature Based Phonetic-Class Pronunciation Modeling."
  In IEEE Trans. on Computers 56 (9), pp. 1189-1198. [BibTex]

Conference Papers:

• S.-X. Zhang and M.J.F. Gales (2013). “Kernelized Log Linear Models For Continuous Speech Recognition.”
  In Proceedings of ICASSP. [BibTex][Poster]

• S.-X. Zhang and M.J.F. Gales (2011). “Extending Noise Robust Structured Support Vector Machines to Larger Vocabulary Tasks.”
  In Proceedings of ASRU, pp. 18-23. [BibTex][Poster]

• S.-X. Zhang and M.J.F. Gales (2011). “Structured Support Vector Machines for Noise Robust Continuous Speech Recognition.”
  In Proceedings of Interspeech, pp. 709-712. [BibTex][Slides] (Best student paper award nominated)

• S.-X. Zhang and M.W. Mak (2009), “Optimization of Discriminative Kernels in SVM Speaker Verification.”
  In Proceedings of Interspeech, pp. 1275-1278.

• S.-X. Zhang and M.W. Mak (2009), "Regression Optimized Kernel for High-Level Speaker Verification."
  In Proceedings of APSIPA, Sapporo, pp. 40-44.

• S.-X. Zhang and M.W. Mak (2008), "High-Level Speaker Verification via Articulatory-Feature based Sequence Kernels and SVM."
  In Proceedings of Interspeech, pp. 1393-1396.

• S.-X. Zhang and M.W. Mak (2008), "Articulatory-Feature based Sequence Kernel For High-Level Speaker Verification."
  In Proceedings of ICMLC, pp. 2799-2804.

• S.-X. Zhang and M. W. Mak (2007), "A New Adaptation Method for Speaker-Model Creation in High-Level Speaker Verification."
  Advances in Multimedia Information Processing, pp. 325-335. [Slides]

• S.-X. Zhang, M. W. Mak and H. Meng (2007), "High-Level Feature-Based Speaker Verification via Articulatory Phonetic-Class Pronunciation Modeling."
  In Proceedings of Interspeech, pp.762-765.

Technical Reports:

• R. C. van Dalen, J. Yang, M. J. F. Gales, A. Ragni and S. X. Zhang (2012).
  “Generative Kernels and Score-Spaces for Classification of Speech: Progress Report.”
  Technical Report CUED/F-INFENG/TR676, Cambridge University Engineering Department, January 2012.

• S.-X. Zhang (2010). “Structured Discriminative Models for Sequential Data Classification.”
  First Year Report, August 2010.

• S.-X. Zhang and M.J.F. Gales (2010). “Structured Log Linear Models for Noise Robust Speech Recognition.”
  Technical report CUED/F-INFENG/TR.658, Cambridge University Engineering Department, July 2010.

Talks/Presentations:

• S.-X. Zhang and M.J.F. Gales (2013). “An Introduction to Structured SVMs for Automatic Speech Recognition”
  Seminar at Cambridge University Engineering Department, February 1, 2013.

• S.-X. Zhang and M.J.F. Gales (2011). “Towards LVCSR System based on Structured SVMs.”
  Seminar at Toshiba Cambridge Research Lab, November 7, 2011.

• S.-X. Zhang. “SayPass Voice Biometric Technology Co., Ltd. Business Plan”
  China-UK High-Level Entrepreneurship Challenge, Semifinal in Oxford, June, 2011.

• S.-X. Zhang and M.J.F. Gales (2011). “Structured SVMs for Continuous Speech Recognition.”
  Seminar at Toshiba Cambridge Research Lab, March 1, 2011.

• S.-X. Zhang and M.J.F. Gales (2010). “Structured SVMs for Continuous Speech Recognition.”
  CUED Internal Presentation to Toshiba, September 7, 2010.

 

• © Shixiong Zhang. Last updated: May 2013.