"Music Technology at Georgia Tech"
Jason Freeman and Parag Chordia, College of Architecture

12:00 Noon on Thursday, February 2, 2006
TSRB 132

What music do you listen to? iTunes Signature Maker (iTSM) seeks to answer this question by representing a user’s musical tastes in a short audio signature. The software stitches together small segments of songs, using an algorithm driven by spectral features intrinsic to the audio files themselves and by environmental features describing how those files have been used. This talk connects iTSM to projects in algorithmic playlist generation and music summarization and then describes the software’s implementation in relation to the project’s objectives: accessibility to a broad audience, accurate representation of users’ musical preferences, and interesting and enjoyable results. The project is evaluated through both statistical data and anecdotal user feedback.

Jason Freeman’s compositions and software art break down conventional barriers between composers, performers, and listeners, using new technologies and extended notation to turn audiences and musicians into compositional collaborators. Current projects include Flock, a full-evening performance for saxophone quartet, audience participation, and real-time video commissioned by the Miami Performing Arts Center; Graph Theory, an Internet-based work commissioned by Turbulence.org; and a new production of Glimmer, a piece for chamber orchestra and audience participation, at the Hamabada Art Center in Jerusalem, Israel. Freeman received his B.A. in music from Yale University and his M.A. and D.M.A. in composition from Columbia University. He is currently an assistant professor of music at Georgia Tech.

Computers play an increasingly important role in creating, analyzing, and finding music. Intelligent interaction depends on the computer "understanding" the musical signal, which concretely means means automatically extracting information such as onset locations, pitch, timbre, musical structure, and genre. This is known generically as music information retrieval (MIR).

Automatic transcription is a form of MIR that focuses on information traditionally found in musical scores. In the past twenty years it has become an active area of research. To date, there is no system that can approach expert human level recognition, but significant progress has been made on the sub-problems of onset detection, tempo and beat detection, pitch and multi-pitch estimation, timbre recognition, and source separation.

This talk will discuss these tasks in the context of automatic transcription solo tabla music. Solo tabla is a sophisticated musical system from India that focuses on timbre and rhythm. Aside from furthering the development automatic transcription techniques, the immediate motivations for this research are to create representations of tabla performances that can be used for analysis and that will allow the musical patterns of tabla music to form the basis for new creative works.

Parag Chordia is an assistant professor of music in the College of Architecture. He is part of the music technology group where he specializes in Music Information Retrieval (MIR) research and applications. Through his research, Dr. Chordia attempts to synthesize advances in pattern recognition and signal processing to create systems that can 'listen' intelligently. He is particularly interested in creating tools that can be used to advance research in computational music theory and music cognition. Dr. Chordia is also interested in the application of MIR tools for composition and multi-media performance. His own compositional work draws on both Indian classical and electronic music traditions.

Dr. Chordia received his PhD in media 'Computer-based Music theory and Acoustics' from Stanford University's CCRMA, and his BA in Applied Mathematics from Yale University. Before turning to academia, he founded Bol Records an Indian classical music label, where he served as CEO and artistic director. Most recently, he co-founded Yaari.com, a social networking tool for South Asians, where he served as CTO. Additionally, he is an active performer of Indian classical music, and a disciple of the legendary Pandit Buddhadev Das Gupta.