Generalization of Supervised Learning for Binary Mask Estimation

Tobias May, Timo Gerkmann

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

1 Downloads (Pure)

Abstract

This paper addresses the problem of speech segregation by es- timating the ideal binary mask (IBM) from noisy speech. Two methods will be compared, one supervised learning approach that incorporates a priori knowledge about the feature distri- bution observed during training. The second method solely relies on a frame-based speech presence probability (SPP) es- timation, and therefore, does not depend on the acoustic con- dition seen during training. We investigate the influence of mismatches between the acoustic conditions used for training and testing on the IBM estimation performance and discuss the advantages of both approaches.
Original languageEnglish
Title of host publicationProceedings of IWAENC 2014
Number of pages5
PublisherIEEE
Publication date2014
ISBN (Print)9781479968084
DOIs
Publication statusPublished - 2014
EventThe International Workshop on Acoustic Signal Enhancement - Antibes - Juan les Pins, France
Duration: 8 Sep 201411 Sep 2014

Conference

ConferenceThe International Workshop on Acoustic Signal Enhancement
CountryFrance
CityAntibes - Juan les Pins
Period08/09/201411/09/2014

Keywords

  • Ideal binary mask
  • Speech segregation
  • Generalization
  • Speech presence probability

Fingerprint Dive into the research topics of 'Generalization of Supervised Learning for Binary Mask Estimation'. Together they form a unique fingerprint.

Cite this