Timezone: »

A Sparse Non-Parametric Approach for Single Channel Separation of Known Sounds
Paris Smaragdis · Madhusudana Shashanka · Bhiksha Raj

Mon Dec 07 07:00 PM -- 11:59 PM (PST) @

In this paper we present an algorithm for separating mixed sounds from a monophonic recording. Our approach makes use of training data which allows us to learn representations of the types of sounds that compose the mixture. In contrast to popular methods that attempt to extract com- pact generalizable models for each sound from training data, we employ the training data itself as a representation of the sources in the mixture. We show that mixtures of known sounds can be described as sparse com- binations of the training data itself, and in doing so produce signi´Čücantly better separation results as compared to similar systems based on compact statistical models.

Author Information

Paris Smaragdis (University of Illinois Urbana-Champaign)
Madhusudana Shashanka (Mars Information Services)
Bhiksha Raj (Carnegie Mellon University)

More from the Same Authors