|
|
Biographical Sketch
I received my Bachelor's degree in Computer Engineering from
the University of Michigan in 1997 and since then, I have been a graduate
student in the Computer Science Division
of the EECS department at the
University of California, Berkeley.
Research
I have been a graduate student researcher in the at the International
Computer Science Institute since 1997. I am a member of the Speech
Group (formerly the Realization
Group).
My research interest lies
in automatic processing of spoken language, melding insights from statistical
analysis of realistic
speech corpora and advanced techniques of machine learning. I am also interested
in applying the concept
and techniques developed from speech research to a broader context of perception,
human-computer interaction,
and language learning.
My official advisor is Prof.
Nelson Morgan, and Dr.
Steven Greenberg and Dr.
Lokendra Shastri are also advising me on my research.
Related links:
LIS (Learning
and Intelligence Systems Initiative) web site
Switchboard
Transcription Project (STP) web site
Phoneval (Diagnostic
Phonetic Evaluation of Hub5 LVCSRs) site
Publications
-
Greenberg, S., Chang, S. and Hitchcock, L. (2001) The Relation
Between Stress Accent and Vocalic Identity in Spontaneous American English
Discourse. Proceedings of the ISCA Workshop on Prosody in Speech Recognition
and Understanding, pp. 51-56. (pdf)
-
Chang, S., Shastri, L. and Greenberg, S. (2001) Robust Phonetic
Feature Extraction Under a Wide Range of Noise Backgrounds and Signal-to-Noise
Ratios. Proceedings of the Workshop on Consistent & Reliable Acoustic
Cues for sound analysis (CRAC 2001), Aalborg, Denmark, Sept., 2001 (pdf)
-
Wester, M., Greenberg, S., Chang, S. (2001) A Dutch Treatment
of an Elitist Approach to Articulatory-Acoustic Feature Classification.
Proceedings of Eurospeech 2001 (pdf)
-
Chang, S., Greenberg, S., Wester, M. (2001) An Elitist Approach
to Articulatory-Acoustic Feature Classification. Proceedings of Eurospeech
2001 (pdf)
-
Chang, S., Shastri, L., Greenberg, G. (2000) Automatic Phonetic
Transcription of Spontaneous Speech (American English) Proceedings of the
International Conference on Spoken Language Processing, Beijing, 2000.
(pdf)
-
Greenberg, S. and Chang, S. (2000) Linguistic dissection
of switchboard-corpus automatic speech recognition systems, Proceedings
of the ISCA Workshop on Automatic Speech Recognition: Challenges for the
New Millenium, Paris, 2000. (pdf)
-
Greenberg, S., Chang, S. and Hollenback, J. (2000) An introduction
to the diagnostic evaluation of the Switchboard-corpus automatic speech
recognition systems. Proceedings of the NIST Speech Transcription Workshop,
College Park, MD, May 16-19, 2000. (pdf)
-
Shastri, L. and Chang, S., A Spatiotemporal Connectionist
Model of Algebraic Rule-Learning, TR-99-011, ICSI, Berkeley, CA,
July, 1999. (postscript,pdf)
-
Shastri, L. Chang, S. and Greenberg, S. (1999) Syllable Detection
and Segmentation Using Temporal Flow Neural Networks. Proceedings of the
Fourteenth International Congress of Phonetic Sciences, San Francisco,
August 1999. (pdf)
Courses
Some past class project reports (in PDF format):
-
CS281b, Advanced Topics in
Learning and Decision Making, Prof. M. Jordan, Spring 2001
Posterior
Probability Estimation using SVM with Noisy Targets
-
CS280, Computer Vision, Prof.
J. Malik, Spring 2000
Non-rigid
Surface Tracking and Modeling Using Stereo Cameras
-
EE225d, Audio Signal Processing
in Humans and Machines, Prof. N. Morgan, Spring 2000
Articulatory
Feature
Extraction Using Temporal Flow Neural Networks
-
CS252, Graduate Computer
Architechture, Prof. J. Kubiatowicz, Fall 1999
An
Efficient Implementation of Hybrid Data Value Predictors with Confidence
Estimation
-
CS281, Machine Learning,
Prof. S. Russel, Spring 1998
Learning
Predictive Evaluation Function for the EM Algorithm
-
CS262, Advanced Operating
Systems, Prof. E. Brewer, Fall 1997
Application-Specific
Memory Management
-
CS294-4, Connectionist and
Neural Computation, Prof. J. Feldman and Dr. L. Shastri, Fall 1997
Modeling
Forgetting - A Computational Model of SMRITI at Cell and Link Level
-
AOSS499 (U. Michigan), Directed
Study, Prof. J. Daida, Spring 1997
A
GP-GA Hybridization System Using a Parasitic Symbiosis Model for Evolving
Wall Following Robot with Parsimonious Sensor Set
Other
|