Selina Chu – Curriculum Vitae

Signal and Image Processing Institute                                                                                                             Phone: (213) 740-3477

3740 McClintock Ave., EEB 400                                                                                                                       Fax: (213) 740-4651

University of Southern California                                                                                                                       Email: selinach@sipi.usc.edu

Los Angeles, CA 90089                                                                                                                                   Web: http://sail.usc.edu/~selinach

RESEARCH INTERESTS

Recognition and analysis of general unstructured acoustic environments, decision-making with multi-modal inputs, machine learning, multitask / transfer learning, data mining, pattern recognition, artificial intelligence

EDUCATION               

Ph.D., Computer Science, University of Southern California (expected December 2009)

Advisors: Shrikanth Narayanan and C.-C. Jay Kuo

M.S., Information and Computer Science, University of California, Irvine, 2002

Area of concentration: Machine Learning / Data Mining

B.S., Electrical and Computer Engineering, California State Polytechnic University, Pomona, 2000

Minor: Computer Science - Artificial Intelligence. Senior project: Micromouse: designed and developed a prototype of a mobile robot using 68HC11 microprocessor.

RESEARCH

Research Assistant, University of Southern California, Los Angeles, CA (08/03 – Present)

Signal Analysis and Interpretation Lab

Research in machine learning and signal processing for analysis of general unstructured audio. Develop algorithms for automatic recognition and characterization of environmental/ambience sounds and for incorporating audio information for autonomous agents.

            Research Scientist / Intern, IBM Research, Cambridge, MA (5/02 – 01/03)

Collaborative User Experience (CUE) Research Group

Planned and conducted a user-study to investigate personal email-experience. Analyzed study-results and developed an email classification system based on the findings using machine learning techniques. Integrated feature selection and weighting of features into the system to improve classification accuracy. Designed a causal dependency network model that incorporates relationships within categories.

            Research Assistant, University of California, Irvine, CA (1/01 – 05/02)

            Data Mining Research in Time-Series

- Designed and developed a novel online algorithm for segmenting time-series using linear piecewise approximation. Also performed an extensive review and empirical comparison of all similar techniques.

- Designed and developed a novel algorithm for performing a query-by-content search using dynamic time warping with probabilistic models that provided a speed up in the orders of magnitude over the classic algorithm.

- Investigated and implemented experiments for indexing of large database.

            Member of Technical Staff / Intern, AT&T Labs-Research, Florham Park, NJ (06/00 – 09/00)

            Speech and Image Processing Research Group

Responsible for design and implementation of a Wizard of Oz experiment to determine an optimal way for users to make travel arrangements in a spoken dialog system. Investigated ways of presenting and negotiating information between users and the system to improve dialog strategies, both in terms of efficiency and user experience, for the AT&T Communicator. Also analyzed data and investigated into modeling spoken human-computer interactions with possible machine learning applications.

Member of Technical Staff / Intern, AT&T Labs-Research, Florham Park, NJ (06/98 – 09/98)

            Speech and Image Processing Research Group

Responsible for design and implementation of a dialog system for children. Created an understanding system to conduct a spelling bee contest. Worked on multimedia output and multi-modal input generalization of the applications.

RESEARCH PROJECT

            NSF VH Museum Guide Project (01/09 – present)

NSF project on creating a virtual museum guide in collaboration with USC Institute for Creative Technologies (ICT) and Boston Museum of Science. Responsible for the audio recognition part, in terms of speech under noisy unstructured environments and recognition of ambiance surrounding the guide.

TEACHING

Teaching Assistant, Graduate course: CS561 Artificial Intelligence, University of Southern California,

Los Angeles, CA (Spring 2007)

Duties included writing examinations, problem and solution sets, grading, and office hours for a course of approximately 85 students.

PUBLICATIONS

Book Chapters

• Chu, S., Narayanan, S., and Kuo, C.-C. J. (2009) “Unstructured Environmental Audio: Representation, Classification and Modeling,” Edited Volume, Machine Audition: Principles, Algorithms and Systems. Published by IGI Global, in review.
• Keogh, E., Chu., S., Hart, D., and Pazzani, M. (2003) “Segmenting Time Series: A Survey and Novel Approach,” Edited Volume, Data Mining in Time Series Databases. Published by the World Scientific Publishing Company.

Journals

• Chu, S., Narayanan, S., and Kuo, C.-C. J. (2009) “Environmental Sound Recognition with Time-Frequency Audio Features,” IEEE Trans. on Speech, Audio, and Language Processing, in press.

Conferences

• Chu, S., Narayanan, S., and Kuo, C.-C. J. (2009) “A Semi-Supervised Learning Approach to Online Audio Background Detection,” Proc. of IEEE Int. Conf. on Acoustics, Speech, and Signal Processing ICASSP-09.
• Chu, S., Narayanan, S., and Kuo, C.-C. J. (2008) “Environmental Sound Recognition using MP-based Features,” Proc. of IEEE Int. Conf. on Acoustics, Speech, and Signal Processing ICASSP-08.
• Chu, S., Narayanan, S., Kuo, C.-C. J., and Mataric', M. J. (2006) “Where Am I? Scene Recognition for Mobile Robots using Audio Features,”   Proc. of IEEE Int. Conf. on Multimedia & Expo ICME-06.
• Chu, S., Narayanan, S., and Kuo, C.-C. J. (2006) “Efficient Rotation Invariant Retrieval of Shapes using Dynamic Time Warping with Applications in Medical Databases,” Proc. of IEEE Int. Symposium on Computer-Based Medical Systems CBMS-06, Special Track on Data Mining.
• Chu, S., Narayanan, S., and Kuo, C.-C. J. (2005) “Towards Parameter-Free Classification of Sound Effects in Movies,” Proc. of SPIE Optics & Photonics, Conf. on Applications of Digital Image Processing XXVIII, v.5909.
• Chu, S., Keogh, E., Hart, D., and Pazzani, M. (2002) “Iterative Deepening Dynamic Time Warping for Time Series,” Proc. of SIAM Int. Conf. on Data Mining SDM-02.
• Keogh, E., Chu., S., Hart, D., and Pazzani, M. (2001) “An Online Algorithm for Segmenting Time Series,” Proc. of IEEE Int. Conf. on Data Mining ICDM-01.
• Keogh, E., Chu., S., and Pazzani, M. (2001) “Ensemble-Index: A New Approach to Indexing Large Databases,” Proc. of ACM Int. Conf. on Knowledge Discovery and Data Mining SIGKDD-01.
• Dutton, D., Chu, S., Hubbell, J., Walker, M., and Narayanan S. (2001) “Amount of Information Presented in a Complex List: Effects on User Performance,” Proc. of Int. Conf. on Human Language Technology Research HLT-01.
• Dutton, D., Chu, S., Hubbell, J., Walker, M., and Narayanan S. (2001) “Just (All) the Facts, Ma'am,” Proc. of Conf. on Human Factors in Computing Systems CHI-01.

Workshops                       

• Chu, S. (2008) “Unstructured Audio Classification for Environment Recognition,” Proc. of 23rd National Conference on Artificial Intelligence AAAI-08, Doctoral Consortium.
• Chu, S., Narayanan, S., and Kuo, C.-C. J. (2006) “Content Analysis for Acoustic Environment Classification in Mobile Robots,” Proc. of AAAI Fall Symposium, Aurally Informed Performance: Integrating Machine Listening and Auditory Presentation in Robotic Systems.
• Keogh, E., Chu., S., and Pazzani, M. (2001) “Using Ensembles of Representations for Indexing Large Databases,” Proc. of Mining Spatial and Temporal Data Workshop at the Fifth Pacific-Asia Conf. on Knowledge Discovery and Data Mining PAKDD-01.

Patents                 

• Chu, S., Dutton, D., Hubbell, J., Narayanan S., and Walker, M., “Dialog adaptation to user questions during information presentation,” Docket Number 2001-0004.

Invited Talks

• “Environmental Sound Recognition with Joint Time- and Frequency-domain Audio Features”, FBK-irst, Trento, Italy, 11-19-07.

PROFESSIONAL REVIEWING

Reviewer

Journals: Pattern Recognition (PR), IEEE Transactions on Audio, Speech and Language Processing (IEEE TASLP), Data & Knowledge Engineering (DKE)

Conferences: European Signal Processing (EUSIPCO), Bio- and Medical Informatics and Cybernetics (BMIC)

External Reviewer

Journals: Journal of Machine Learning (JML), European Association for Signal and Image Processing (EURASIP), Journal on Audio, Speech, and Music Processing (JASMP)

Conferences: ACM SIGMOD, ACM Multimedia, IEEE ICDE

PROFESSIONAL AFFILIATIONS / HONORS / GRANTS

National Electrical Engineering Honor Society (Eta Keppa Nu), member

National Engineering Honor Society (Tau Beta Pi), member

American Association for Artificial Intelligence (AAAI), member

Institute of Electrical and Electronics Engineers (IEEE), member

GAANN fellowship recipient 1999-2002

SIGART/AAAI Doctoral Consortium Scholarship 2008

WISE Travel Grant (for the ICASSP meeting in Taipei, Taiwan, 2009), $700