| Abstract: |
The singing voice is the oldest and most variable of musical instruments. By combining music, words, and expression, the voice is able to affect us in ways that no other instrument can. But the acoustic flexibility of the voice in intimating words, shaping phrases, and conveying emotion also makes it the most difficult instrument to model computationally. Moreover, while all voices are capable of producing the common sounds necessary for language understanding and communication, each voice possesses distinctive features seemingly independent of phonemes and words. These unique acoustic qualities are the result of a combination of innate physical factors and expressive characteristics of performance, reflecting an individual's vocal identity.
A great deal of prior research has focused on speech coding, speech recognition, and speaker identification, but relatively little work has been performed specifically on singing. There are significant differences between speech and singing in terms of both production and perception. Traditional computational models of speech have focused on the intelligibility of language, often sacrificing sound quality for model simplicity. Such models, however, are detrimental to the goal of singing, which relies on acoustic authenticity for the non-linguistic communication of expression and emotion. These differences between speech and singing dictate that an alternative representation is needed to capture the sound quality and musicality most valued in singing. This talk will describe several approaches specific to the singing voice demonstrated to be useful for a variety of applications, such as singing voice coding, automatic singer identification, and voice transformation.
|
| Bio: |
Youngmoo Kim received his Ph.D. from the MIT Media Lab in 2003, where his thesis research explored coding and synthesis of the singing voice. As a graduate student in the Machine Listening Group under the supervision of Professor Barry Vercoe, he pursued research in audio signal processing, music encoding, and music information retrieval. He was an active member of the MPEG standards committee, contributing to the MPEG-4 and MPEG-7 audio standards. In addition to his Masters in Electrical Engineering, he also holds a Masters degree in vocal performance (both from Stanford University). He is currently a Senior Research Scientist at Nellymoser, Inc., a company focused on audio technologies for emerging markets such as console video games and mobile entertainment. He is pursuing advanced coding technologies for speech and audio with a particular emphasis on voice modification. Youngmoo is also a member of the Tanglewood Festival Chorus, the chorus of the Boston Symphony Orchestra.
|