The Role of Subglottal Resonances in Machine-Based Speech Processing Applications – Abeer Alwan (UCLA)

When:
April 3, 2015 all-day
2015-04-03T00:00:00-04:00
2015-04-04T00:00:00-04:00

Abstract
The subglottal acoustic system refers to the acoustic system below the glottis, which consists of the trachea, bronchi and lungs. Resonances of this system have not been investigated before in speech processing applications. Our work was motivated by the observations that the first and second subglottal resonances (Sg1) and (Sg2) form phonological vowel feature boundaries, and that SGRs, especially SG2, are fairly constant for a given speaker across phonetic contexts and languages. After collecting an acoustic and subglottal database of 50 adults and 50 children, analyzing the database, and developing algorithms to estimate robustly SGRs, we were able to use these resonances to improve the performance of a variety of speech processing systems. These include recognition of children’s speech in limited-data situations, frequency-warping experiments for adult speech recognition, speaker recognition and verification experiments, and automatic height estimation. These experiments were performed with the TIMIT, TIDIGITS, WSJ, AURORA-4, and NIST 2008 databases. [Work supported in part by the NSF].

Biography
Abeer Alwan received her Ph.D. in EECS from MIT in 1992. Since then, she has been with the EE Department at UCLA where she is now a Full Professor. Her research interests include modeling human speech production and perception mechanisms and applications of these models. She is the recipient of the NSF Research Initiation and Career Awards, NIH FIRST Award, UCLA-TRW Teaching Award, and the Okawa Foundation Award in Telecommunications. Dr. Alwan is a Fellow of the IEEE, American Institute of Physics, and the International Speech Communication Association (ISCA). She was an Editor-in-Chief for Speech Communication, and an Associate Editor for several other publications. She is the Vice Chair of the IEEE AB ARC Awards committee. She was a Fellow of the Radcliffe Institute for Advanced Study at Harvard, and a Distinguished Lecturer for ISCA and the Asia Pacific Signal and Information Processing Association.

Center for Language and Speech Processing