Chao Wang

Education

Massachusetts Institute of Technology, Cambridge, MA, 9/95-5/01
Master of Science degree in Electrical Engineering and Computer Science in 5/97. PhD degree in Electrical Engineering and Computer Science in 5/01. GPA = 5.0/5.0.

Honor: Eurospeech'97 excellent student paper acknowledgement.

Graduate-Level Courses: Digital Signal Processing; Stochastic Processes, Detection, and Estimation; Discrete Stochastic Processes; Speech Communication; Digital Speech Processing; Automatic Speech Recognition; Introduction to VLSI systems; Anatomy; Physiology of Hearing; German(I, II).

Tsinghua University, Beijing, China, 9/89-7/94
Bachelor of Engineering degree in Biomedical Engineering & Instrumentation with minor in Computer Science & Technology in 7/94. GPA = 92/100.

Honors: Excellent Student Scholarship Award Recipient (1990-1993), Dean's List 1994.

Skills

Computer: C, Perl, Tcl/Tk, MATLAB
Languages: Fluent in English and Mandarin Chinese, basic knowledge of German.

Research Experience

Massachusetts Institute of Technology, Cambridge, MA, 6/01-present
Research Scientist: Research activities and interests include multilingual dialogue systems, foreign language teaching systems, paralinguistics in speech communicaiton, and issues in human-computer interactions in general.

Massachusetts Institute of Technology, Cambridge, MA, 9/97-5/01
Research Assistant: Completed a Doctoral Thesis on prosodic models for improved speech recognition and understanding in dialogue systems under Dr. Stephanie Seneff (2001). Designed and implemented a pitch tracking algorithm that is particularly robust for telephone speech and prosodic modeling applications. Investigated the use of sublexical prosodic constraints to improve recognition of Mandarin Chinese and English speech. Improved the performance of recognition confidence scoring using prosodic cues. Researched a framework for characterizing intonation contours in English without intermediate prosodic transcriptions. Additional projects included developing a Mandarin Chinese version of the JUPITER weather information system (2000). For this project, developed hierarchical N-gram language models and implemented a procedure to automatically derive diphone classes using decision tree clustering techniques.

SpeechWorks International , Boston, MA, Summer '97
Software Engineer: Developed Mandarin speech recognition systems for stock names and digit strings. Implemented a Mandarin Chinese stock quote demo system for the Taiwan stock market.

Massachusetts Institute of Technology, Cambridge, MA, 3/96-5/97
Research Assistant: Completed a Master's Thesis on porting the GALAXY system to Mandarin Chinese under Dr. Stephanie Seneff (1997). Developed speech recognition, language understanding and language generation components for Mandarin Chinese, with emphasis on Chinese-specific issues. Collected and transcribed Mandarin speech data from native speakers for system training and evaluation. View a demo (size: 11.5Mb) of the system if you are interested.

Tsinghua University, Beijing, China, 9/93 - 7/94
Research Assistant: Completed a Bachelor's Thesis under the supervision of Professor Qinyu Tang on the development of a prototype instrument for measuring brain evoked potentials (1994). Designed and tested amplification, data sampling, and control logic circuits. Wrote graphical user interface and driver software using C and Assembly.

Teaching Experience

Massachusetts Institute of Technology, Cambridge, MA, Spring '99
Teaching Assistant: Prepared homework/laboratory assignments and solutions, conducted laboratory sessions, maintained course webpage, handled student questions, and graded homework for graduate-level course in Automatic Speech Recognition (6.345).

Publications

Wang, C., and Seneff, S., "Prosodic scoring of recognition outputs in the JUPITER domain," In Proceedings of 2001 ISCA Workshop on Prosody in Speech Recognition and Understanding , Red Bank, NJ - USA, October, 2001.

Wang, C., and Seneff, S., " Lexical stress modeling for improved speech recognition of spontaneous telephone speech in the JUPITER domain," In Proceedings of the 7th European Conference on Speech Communication and Technology, Aalborg - Denmark, September, 2001. Acrobat (PDF) file

Tang, M., Wang, C., and Seneff, S., " Voice transformations: from speech synthesis to Mammalian vocalizations," In Proceedings of the 7th European Conference on Speech Communication and Technology, Aalborg - Denmark, September, 2001.

Wang, C., Prosodic Modeling for Improved Speech Recognition and Understanding, PhD Thesis, MIT, May 2001. Acrobat (PDF) file

Wang, C., Cyphers, S., Mou, X., Polifroni, P., Seneff, S., Yi, J., and Zue, V., "MUXING: a telephone-access Mandarin conversational system," In Proceedings of the 6th International Conference on Spoken Language Processing, Beijing - China, October, 2000. Acrobat (PDF) file

Wang, C., and Seneff, S., "Improved tone recognition by normalizing for coarticulation and intonation effects," In Proceedings of the 6th International Conference on Spoken Language Processing, Beijing - China, October, 2000. Acrobat (PDF) file

Wang, C., and Seneff, S., "Robust Pitch Tracking for Prosodic Modeling in Telephone Speech," In Proceedings of the 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing, Istanbul - Turkey, June, 2000. Acrobat (PDF) file

Wang, C., and Seneff, S., "A study of tones and tempo in continuous Mandarin digit strings and their application in telephone quality speech recognition," In Proceedings of the 5th International Conference on Spoken Language Processing, Sydney - Australia, November, 1998. Acrobat (PDF) file

Wang, C., Glass, J., Meng, H., Polifroni, J., Seneff, S., and Zue, V.W., "YINHE: a Mandarin Chinese version of the GALAXY system," In Proceedings of Eurospeech-97, Rhodes - Greece, September 1997. Acrobat (PDF) file

Wang, C., Porting the GALAXY System to Mandarin Chinese, S.M. Thesis, MIT, May 1997. Acrobat (PDF) file