Music Technology Group

Music Department, College of Architecture, Georgia Institute of Technology

Parag Chordia

Bio

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.


Current/Recent Research

Accounting for Tonal Qualia in Hindustani Music: A Statistical Learning Approach

When listening to music, different tones evoke different phenomenal experiences. In both Western and non-Western music, listeners report that tones variously evoke a sense of expectation, anticipation, surprise, instability, inappropriateness, poignancy, strength, energy, repose, etc. In different contexts the same pitch may evoke dramatically different qualia. What accounts for the different qualia experiences? That is, what contextual properties contribute to the distinctive feelings evoked by a tone? This research proposes to address this question from the perspective of statistical learning. In particular, can statistical learning account for some of the phenomenal experiences evoked by listeners of Hindustani music. (Parag Chordia, David Huron)


Automatic Melody Transcription in Indian Classical Music

Indian Classical Music presents an interesting case for melodic transcription due to the complexity and fluidity of the melody and because no symbolic scores exist. Because of this, automatic transcription tools are particularly relevant. The current research attempts to separate the melodic line from a polyphonic mixture containing tabla (pitched percussive accompaniment) and tanpura (timbrally rich drone). The isolated line is then pitch tracked to create a continuous pitch vs. time representation which can be used to derive more abstract symbolic representations to study a variety of fundamental questions: What types of micro-tonal inflections are used in Hindustani music? Can melodies be identified from the distribution of notes used in passages? What expressive effects are used to highlight melodic expressions?  (Parag Chordia)

Automatic Transcription of Tabla 

Tabla is the most important percussion instrument in North India; its distinctive timbre is ubiquitous in classical, folk, and popular music. Tabla music is a sophisticated improvisation-based system that focuses on timbre and rhythm, with a complex fingering technique that allows performers to crisply juxtapose strokes of differing timbres. This research attempts to teach a machine to perceive the timbral and rhythmic structure of tabla music. Aside from furthering research in automatic transcription, 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)


Listening Machines

Listening Machines is a concert series featuring pieces by the faculty and students from Georgia Tech's Music Technology group. The concert series explores concepts of machines listening and improvisation and musical human-machine interaction. (Gil Weinberg, Jason Freeman, Parag Chordia, Frank Clark, Chris Moore, Scott Driscoll, Travis Thatcher, Mark Godfrey)


Publications

2007

Chordia, P., Rae, A. "Modeling and Visualizing Tonality in N. Indian Classical Music."  In Proc. of the 2007 Neural Information Processing Systems Foundation (NIPS). (submitted)


Chordia, P., Rae, A. "Automatic Raag Classification Using Pitch-class and Pitch-class Dyad Distributions." In Proc. of the 7th International Conference on Music Information Retrieval (ISMIR). (pdf) (presentation slides)


Chordia, P., Rae, A. "Understanding Emotion in Raag: An Empirical Survey of Listener Responses." In Proc. of the 2007 International Computer Music Conference (ICMC). (pdf) (presentation slides)


Chordia, P., Rae, A. "Relating Judgments of Dissonance to Sensory Consonance in the Context of Indian Classical Music" Abstract In Proc. of the 2007 Society for Music Perception and Cognition (SMPC). (pdf)


Chordia, P. " A System for the Analysis and Representation of Bandishes and Gats Using Humdrum Syntax." In Proc. of the 2007 Frontiers of Research in Speech and Music Conference (FRSM 2007). (pdf)


2006

Chordia, P. “Understanding micro-pitch structure in Raag Darbari.” Journal of the Sangeet Research Academy.

 

Chordia, P. “Automatic raag classification of pitch-tracked performances using pitch-class and pitch-class dyad distributions.” In Proceedings of the 2006 International Computer Music Conference (ICMC).

 

Chordia, P. “Automatic transcription and representation of solo tabla music.” Computing in Musicology. Vol. 13.

 

Chordia, P. Automatic transcription of solo tabla music. Ph.D. dissertation, Stanford University. 


2005

Chordia, P. “Segmentation and recognition of tabla strokes.” In Proc. of the 6th International Conference on Music Information Retrieval (ISMIR), pages 107-114.


Chordia, P. “Automatic labeling of tabla strokes”. Journal of the Sangeet Research Academy. 


2004

Chordia, P. “Automatic rag classification using spectrally derived tone profiles.” In Proceedings of the 2004 International Computer Music Conference (ICMC).

Music Department, 840 McMillan St., Atlanta, GA USA, 30332-0456 TEL: 404.894.8949  FAX: 404.894.9952