Computer Science Colloquia
Friday, April 19, 2013
Advisor: Jack Stankovic
Attending Faculty: Kamin Whitehouse(Chair), Alfred Weaver, John Lach, and Stephen G. Wilson (minor representative)
3:00 PM, Rice Hall, Rm. 204
PhD Proposal Presentation
A General-Purpose, Energy-Efficient, and Context-Aware Acoustic Event Detection Service for Smartphones
We propose a mobile-cloud service platform for detecting and classifying high-level acoustic events sensed by the microphone on a smartphone -- which is (1) more generic, (2) highly accurate, (3) more energy-efficient, (4) adaptive to change of context, and (5) easier to program than both fixed classifiers running on a smartphone and web-services for classifying acoustic events on a smartphone. We name the platform Auditeur (means listener in French). Auditeur enables developers have their app to register for and get notified on a wide variety of acoustic events. Auditeur is backed by a cloud service to store user contributed sound clips and to generate an energy-efficient and context-aware classification plan for the phone. When an acoustic event type has been registered by an app, the smartphone instantiates the necessary acoustic processing modules and wires them together to execute the plan. The phone then captures, processes, and classifies acoustic events locally and efficiently. This proposal provides an overview of Auditeur platform along with key research questions, an evaluation plan, and some preliminary results.