On Tuesday 18th June at 3pm, Prof Bryan Pardo will present the seminar ‘Computer Audition – Analyzing Complex Auditory Scenes‘.
The talk will take place in room AG03 (College building, City University London) – click here for a map.
Title: Computer Audition – Analyzing Complex Auditory Scenes
Speaker: Prof Bryan Pardo (Northwestern University)
Computer audition is the study of how to design computational elements systems that are able to access, separate and manipulate sound sources in complex audio mixtures, such as a cocktail party. Problems in this field include source separation (splitting audio mixtures into individual sounds), source discovery (finding and labeling a sound source in a scene), and streaming (finding which sounds belong to a single source). One of the biggest challenges in computer audition comes from the fact that most auditory scenes are complex: Different sound sources often overlap and interfere with each other at the same time and frequency. Furthermore, the ways that these sources mix together and the source signals themselves are constantly changing. Therefore, systems must leverage multiple kinds of information and analysis at different levels of abstraction to succeed. This talk will cover recent work in Bryan Pardo’s lab on three aspects of computer audition: 1) sound source discovery (e.g. estimating concurrent pitches of multiple harmonic sources at a given time); 2) audio source separation (e.g. streaming pitches of the same source across time and separating its signal from the mixture); and 3) leveraging external information (e.g. a musical score) to improve separation and manipulation of sound objects and sources.
Bryan Pardo, head of the Northwestern University Interactive Audio Lab, is an associate professor in the Northwestern University Department of Electrical Engineering and Computer Science with an additional appointment in the Music Theory and Cognition Department. Prof. Pardo received a M. Mus. in Jazz Studies in 2001 and a Ph.D. in Computer Science in 2005, both from the University of Michigan. He has authored over 70 peer-reviewed publications. He is an associate editor for IEEE Transactions on Audio Speech and Language Processing. He has developed speech analysis software for the Speech and Hearing department of the Ohio State University, statistical software for SPSS and worked as a machine learning researcher for General Dynamics. While finishing his doctorate, he taught in the Music Department of Madonna University. When he’s not programming, writing or teaching, he performs throughout the United States on saxophone and clarinet at venues such as Albion College, the Chicago Cultural Center, the Detroit Concert of Colors, Bloomington Indiana’s Lotus Festival and Tucson’s Rialto Theatre. Website: http://www.cs.northwestern.edu/~pardo/