Recognition of convolutive speech mixtures by missing feature techniques for ICA

Dorothea Kolossa, Hiroshi Sawada, Ramon Fernandez Astudillo, Reinhold Orglmeister, Shoji Makino

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

One challenging problem for robust speech recognition is the cocktail party effect, where multiple speaker signals are active simultaneously in an overlapping frequency range. In that case, independent component analysis (ICA) can separate the signals in reverberant environments, also. However, incurred feature distortions prove detrimental for speech recognition. To reduce consequential recognition errors, we describe the use of ICA for the additional estimation of uncertainty information. This information is subsequently used in missing feature speech recognition, which leads to far more correct and accurate recognition also in reverberant situations at RT60 = 300ms.

Original languageEnglish
Title of host publicationConference Record of the 40th Asilomar Conference on Signals, Systems and Computers, ACSSC '06
Pages1397-1401
Number of pages5
DOIs
Publication statusPublished - 2006
Externally publishedYes
Event40th Asilomar Conference on Signals, Systems, and Computers, ACSSC '06 - Pacific Grove, CA, United States
Duration: 2006 Oct 292006 Nov 1

Publication series

NameConference Record - Asilomar Conference on Signals, Systems and Computers
ISSN (Print)1058-6393

Conference

Conference40th Asilomar Conference on Signals, Systems, and Computers, ACSSC '06
Country/TerritoryUnited States
CityPacific Grove, CA
Period06/10/2906/11/1

ASJC Scopus subject areas

  • Signal Processing
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Recognition of convolutive speech mixtures by missing feature techniques for ICA'. Together they form a unique fingerprint.

Cite this