Linear Regression on Sparse Features for Single-Channel Speech Separation

Mikkel N. Schmidt, Rasmus Kongsgaard Olsson

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    497 Downloads (Pure)

    Abstract

    In this work we address the problem of separating multiple speakers from a single microphone recording. We formulate a linear regression model for estimating each speaker based on features derived from the mixture. The employed feature representation is a sparse, non-negative encoding of the speech mixture in terms of pre-learned speaker-dependent dictionaries. Previous work has shown that this feature representation by itself provides some degree of separation. We show that the performance is significantly improved when regression analysis is performed on the sparse, non-negative features, both compared to linear regression on spectral features and compared to separation based directly on the non-negative sparse features.
    Original languageEnglish
    Title of host publicationApplications of Signal Processing to Audio and Acoustics : IEEE Workshop on (WASPAA)
    PublisherIEEE
    Publication date2007
    ISBN (Print)978-1-4244-1620-2
    DOIs
    Publication statusPublished - 2007
    Event2007 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics - New Paltz, United States
    Duration: 21 Oct 200724 Oct 2007

    Conference

    Conference2007 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics
    Country/TerritoryUnited States
    CityNew Paltz
    Period21/10/200724/10/2007

    Bibliographical note

    Copyright: 2007 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE

    Fingerprint

    Dive into the research topics of 'Linear Regression on Sparse Features for Single-Channel Speech Separation'. Together they form a unique fingerprint.

    Cite this