• home
• current students
• graduate
• events

Presenter: Dr. George Tzanetakis - Post Doctoral Fellow, Computer Science Department, Carnegie Mellon University
Supervisor: R. Nigel Horspool, Chair Department of Computer Science

Date: Thu, February 27, 2003
Time: 13:30:00 - 14:30:00
Place: Engineering Office Wing Building(EOW), Room # 430

ABSTRACT

ABSTRACT:

As hard disk capacity and network bandwidth keep increasing so does our ability to store and distribute large collections of multimedia information. A large part of multimedia data and internet traffic in general consists of music stored in compressed audio files. It is very likely that in the near future all of recorded music will be available digitally. In order to fully take advantage of this great possibility it is necessary to provide tools to search, organize and explore these vast amounts of musical data. Unlike current audio software tools which are agnostic to audio content and treat it as a monolithic block of digital samples, new software tools must be able to automatically extract content information and have some "understanding" of the music.

In this talk, I will describe some examples of such musical content understanding algorithms and systems that I have worked on. These include: automatic musical genre classification, content-based similarity retrieval, compressed-domain feature extraction, content and context aware user interfaces, and structural analysis. This work falls under the general area of Computer Audition and more specifically under Music Information Retrieval (MIR) which is a growing research area that deals with the problem of effectively searching, analyzing and exploring large collections of music. In order to extract information from "real-world" complex audio signals such as music files on the web, the developed algorithms and systems combine ideas from Signal Processing, Machine Learning and Human Computer Interaction. All of this work can be viewed as building the foundations for creating digital libraries of music that support various ways of interaction based on automatic understanding of musical signals in audio format.

Note: Dr. George Tzanetakis is a candidate for a faculty position in the Department of Computer Science.