Welcome to Xiong Xiao's Webpage!

	Xiong XIAO PhD candidate Center for Multimedia and Networking Technologies School of Computer Engineering Nanyang Technological University N4-B2C-06, Nanyang Avenue, Singapore 639798 Email: xiao0007@ntu.edu.sg

Education

2004-Present: PhD candidate in School of Computer Engineering, Nanyang Technological University, Singapore.
2000-2004: Graduated with the first class honors in B.Eng (Computer Eng.), School of Computer Engineering, Nanyang Technological University, Singapore.
Dec 1999 - Jun 2000: Pre-college course, National University of Singapore, Singapore
1996-1999: Jinyuan Senior Middle school, Dayi County, Sichuan Province, China
1993-1996: Jinyuan Junior Middle school, Dayi County, Sichuan Province, China

PhD Research

Topic: Noise robust speech recognition technique
Introduction: Speech recognition is a core technology for human-machine communication. The state-of-the-art speech recognition systems using a statistical framework achieve high recognition accuracy in clean environment and for constrained speaking style speech. However, under adverse environment and more flexible speaking style, the recognition accuracy degrades significantly. The robustness of the speech recognition system against the environment and speaking style are two important research area in speech recognition. My research is focused on the former issue.

To have an overview of the current noise robust speech recognition techniques, please read the literature review chapter of my first year report (FYR).

See my research page
See my research proposal

My supervisors

Principle superviosr: Dr. Eng Siong Chng, School of Computer Engineering, Nanyang Technological Universicy, Singapore
Co-supervisor: Dr. Haizhou Li, Institute for Infocomm Rearch (I2R), Agency for Science, Technology and Research (A*STAR), Singapore

Publications

Journal

Xiong Xiao, Eng Siong Chng, and Haizhou Li, "Temporal structure normalization of speech feature for robust speech recognition", IEEE Signal Processing Letters, vol. 14, no. 7, pp. 500-503, July 2007.
Xiong Xiao, Eng Siong Chng, and Haizhou Li, "Normalization of speech modulation spectra for robust speech recognition", IEEE Transactions on Audio, Speech, and Language Processing, vol. 16, no. 8, pp. 1662-1674, November 2008.
Xiong Xiao, Jinyu Li, Eng Siong Chng, Haizhou Li, and Chin-Hui Lee, "A Study on the Generalization Capability of Acoustic Models for Robust Speech Recognition", IEEE Transactions on Audio, Speech, and Language Processing, vol. 18, no. 6, pp. 1158-1169, August 2010.

Conference

Xiong Xiao, Haizhou Li, and Eng Siong Chng, "Vector autoregressive model for missing feature reconstruction", in Proceedings of International Symposium on Chinese Spoken Language Processing 2006, LNAI, Vol. 4274, Q. Huo, B. Ma, E.-S. Chng and H. Li (Eds), pp. 315-324, 13-16 December, Singapore.
Xiong Xiao, Eng Siong Chng, and Haizhou Li, "Normalizing the speech modulation spectrum for robust speech recognition", in the proceeding of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '07), vol. IV, pp. 1021-1024, 15-20 April, 2007, Hawaii, USA.
Xiong Xiao, Eng Siong Chng, and Haizhou Li, "Evaluating the temporal structure normalization technique on the Aurora-4 task", in the proceedings of InterSpeech 2007, pp. 1070-1073, August 27-31, 2007, Antwerp, Belgium.
Di Gao, Xiong Xiao, Guangxi Zhu, Eng Siong Chng, and Haizhou Li, "Classification of Speech Transmission Channels: Landline, GSM and VoIP Networks", in proceedings of International Conference on Signal Processing (ICSP 08).
Xiong Xiao, Eng Siong Chng, Haizhou Li, and Di Gao, "Automatic Identification of Speech Transmission Channels for Voice Data Collection", in proceedings of Oriental COCOSDA 08.
Xiong Xiao, Eng Siong Chng, and Haizhou Li, "Effect of feature smoothing for robust speech recognition", in the proceedings of ISCSLP 2008, pp. 1-4, December 16-19, 2008, Kunming, China.
Tien-Ping Tan, Xiong Xiao, Enya Kong Tang, Eng Siong Chng, and Haizhou Li, "MASS: A Malay Language LVCSR Corpus Resource", in proceedings of Oriental COCOSDA 2009.
Xiong Xiao, Jinyu Li, Eng Siong Chng, Haizhou Li, and Chin-Hui Lee, "A Study on Hidden Markov Model's Generalization Capability for Speech Recognition", in Proceedings of ASRU 2009, pp. 255-260, December 13-17, 2009, Merano, Italy.

Technical Report

Xiong Xiao, "Speech enhancement with applications in speech recognition", first year report, School of Computer Engineering, Nanyang Technological University, Singapore, 2005

PhD Thesis

Xiong Xiao, "Robust speech features and acoustic models for speech recognition", PhD thesis, School of Computer Engineering, Nanyang Technological University, Singapore, 2009

Technical Writing

Technical Writing Skills

Purdue University's OWL English workshop, Click here.
The Element of Style by Strunk William, Click here.
Cite in a professional way. Examples of the University of Toronto: example a, example b
The way to introduce notations with lots of equations and variables. See this paper.

LaTex

Managing Citations. BibTex is a good way to manage citations in the TeX environment. Google it to find out tutorials this topic.
My BibTex file on robust speech recognition.
Current there are around 100 citations in the .bib file. I will keep updating it.
Download it here: the header file, the entry file
A report template with examples of common functions of LaTex. Download here

My Life:)