Shrikanth (Shri) Narayanan
Location: (Los Angeles, CA)
Personal Research Web Page: http://sail.usc.edu/shri
Keywords: speech, audio, language, gestures, affect, emotion, biomedical, multimodal, speech recognition, translation, synthesis, articulatory models, multimedia, virtual humans, interfaces, speech production
Posted on: Tuesday, May 26th, 2009
Broad Research Area: AI / Machine Learning / Robotics / Vision, HCI / CSCW
Research Interests:
SAIL’s contributions are in the broad area of human-centric multimodal signal processing and applications spanning speech, audio, image and bio signal processing, The work uniquely bridges science and engineering through interdisciplinary approaches and the contributions integrate fundamental and applied problems in human communication. The effort is distinctive: On the one hand, it has used signal processing advances to further fundamental understanding of human speech communication (e.g., modeling speech, language, gestures, and emotions), while on the other hand, it has synthesized and leveraged unique data and interdisciplinary scientific knowledge to develop cutting-edge multimedia technologies for applications ranging from education to military and business (technologies for children and education, military simulation and training using virtual human technologies and novel multilingual translation systems).
This research group is devoted to theoretical issues and practical applications of:
* Speech, Language and Multimodal Information Processing; Automatic Speech/Speaker Recognition; Speech Translation; Audio-visual processing
* Speech Production Modeling, Articulatory Acoustics, Speech Synthesis
* Biomedical Signal Processing and Modeling; Imaging & Instrumentation for Speech Research
http://sail.usc.edu/span
* Emotions research: analysis, recognition and expressive synthesis
http://sail.usc.edu/emotion
* Human Machine Interaction; Multimodal-Multimedia Interfaces, Devices, and Systems
Research projects involve graduate and undergraduate students as well as a number of faculty and industry collaborators. Although primarily SAIL students come from Electrical Engineering or Computer Science, students from the Annenberg School of Communication and the Linguistics and Psychology departments participate in our research through collaborative projects. SAIL is a part of the Signal and Image Processing Institute (SIPI) and has ties with the USC Information Sciences Institute (www.isi.edu)and Institute for Creative Technologies (ict.usc.edu).
Recent SAIL highlights include a 2005 IEEE Signal Processing Society Best Paper Award for work on technology for children, as well as best student paper awards at the 2005 IEEE ICASSP on automatic prosody detection from speech and language, a 2006 IEEE MMSP paper award for signal and language based representation of audio, a paper award in IEEE 2007 MMSP for work on user modeling of multimodal interface use and a DCOSS’2009 applications/systems best paper award for collaborative work among several colleagues and students on body computing. SAIL’s work on emotion recognition provides a novel framework for measuring and modeling emotion information from various information sources (speech, gestures, language, and context) has garnered wide attention.
Contact Information:
Email: email obfuscated - click to reveal
Telephone: 213 740 6432
