
Established in 1992, our laboratory conducts research in a wide range of
areas in speech processing. Our research interests focus on developing quantitative
models of human speech perception and production mechanisms and using these
models to improve the performance of speech-processing applications. These
quantitative models are essential for providing insights into our cognitive
abilities. Our research activities include: Modeling Speech Perception in Noise
with Applications to Speech Coding, Hearing Aids and Automatic Speech
Recognition; Novel Techniques for Modeling Speech Production; Synthesis of
Pathological Voices; Acoustic Echo Cancelation; and Acoustically-driven Talking
Face Animation. The projects foster
cross-disciplinary activities in the Engineering, Computer Science, Graduate School of Education
and Information Science, Radiology, Linguistics, Head and Neck Surgery, and Neurosurgery
Departments at UCLA and with researchers at the House Ear Institute .
Support for
this research is provided by contracts and grants from several agencies of the
federal government as well as from industrial sources. We are currently
supported by NSF, NIH, HRL , Broadcom,
and ST Microelectronics.
SPAPL is a part of the Electrical
Engineering Department of UCLA.
The laboratory is equipped with Sun and HP workstations, audio equipment, a
high quality sound-level meter, and a sound-insulated booth. The lab is located
in 63-134N Engineering IV on the UCLA campus.
This page is maintained by Jonas Borgstrom (jonas@ee.ucla.edu)
Back to UCLA Electrical
Engineering home page