Event
Ph.D. Dissertation Defense: Lakshmi Krishnan
Monday, October 5, 2015
2:00 p.m.
AVW 2460
Maria Hoo
301 405 3681
mch@umd.edu
ANNOUNCEMENT: Ph.D. Dissertation Defense
Location: AVW 2460
Title: Mechanisms behind sound source segregation
Abstract:
While humans can easily segregate and track a speaker's voice in a loud noisy
environment, most modern speech recognition systems still perform poorly in loud
background noise. The computational principles behind auditory source segregation
in humans are not yet fully understood. In this dissertation, we develop a
computational model for source segregation inspired by auditory processing in the
brain. To support the key principles behind the computational model, we conduct a
series of electro-encephalography experiments using both simple tone-based
stimuli and more natural speech stimulus.
Most source segregation algorithms utilize some form of prior information about
the target speaker or use more than one simultaneous recording of the noisy speech
mixtures. Other methods develop models on the noise characteristics. Source
segregation of simultaneous speech mixtures with a single microphone recording
and no knowledge of the target speaker is still a challenge. Using the principle of
temporal coherence, we develop a novel computational model that exploits the
differences in the temporal evolution of the features that belong to different sources,
to perform unsupervised monaural source segregation. While using no prior
information about the target speaker, this method can gracefully incorporate
knowledge about the target source, if available, to further enhance the segregation.
Using this model, we are able to segregate speech from speech in noise, speech in
music sand speech mixtures. Aside from its unusual structure and computational
innovations, the proposed model provides testable hypotheses of the physiological
mechanisms of the remarkable perceptual ability of humans to segregate acoustic
sources, and of its psychophysical manifestations in navigating complex sensory
environments.
Next, through a series of EEG experiments we collect neurological evidence to
support the principle behind the model. We conduct EEG experiments to contrast
the neural signatures of synchronous and alternating tone sequences and study the
influence of attention on the measured neural response. Finally, we build an online
decoder in sensor space to decode auditory attention from EEG. Results from EEG
experiments provide further insights into the assumptions behind the
computational model and provide motivation for future single unit studies that can
provide more direct evidence for the principle of temporal coherence.
Maria C. Hoo
Graduate Studies Office (GSO)
2434 AV Williams Building
301-405-3681 (Phone)
301-405-8728 (Fax)