ISSE: An Interactive Source Separation Editor, Part II

Date: 
Tue, 11/12/2013 - 5:30pm - 6:45pm
Location: 
CCRMA Classroom
Event Type: 
DSP Seminar

Abstract:  In the second talk of a two-part series, we will further discuss ISSE--an interactive source separation editor.  As described earlier, ISSE is a new, open-source, freely available, cross-platform audio editing software tool which enables a user to perform single-channel source separation by painting on time-frequency visualizations of sound. It is useful for a variety of music- and audio-related tasks such as music remixing, audio denoising, and audio-based forensics.   

 
In contrast to the first talk, we will go in-depth into the technical approach of the work. To do so, we will begin with an overview of non-negative matrix factorization and related probabilistic separation techniques. We will then discuss the use of user-feedback, which is used to significantly improve separation quality and achieve state-of-the-art separation quality for a wide variety of sound. For more information, please see http://isse.sourceforge.net and https://ccrma.stanford.edu/~njb/research/

Speaker Bio: Nicholas J. Bryan is a PhD candidate working with Prof. Ge Wang at CCRMA and Gautham J. Mysore at Adobe Research. His research interests are at the intersection between signal processing, machine learning, and human-computer interaction.

FREE
Open to the Public
Syndicate content