Joint Single-Channel Speech Separation and Speaker Identification

Pejman Mowlaee, Rahim Saeidi, Zheng-Hua Tan, Mads Græsbøll Christensen, Pasi Fränti, Søren Holdt Jensen

Research output: Contribution to journalConference article in JournalResearchpeer-review

17 Citations (Scopus)
928 Downloads (Pure)

Abstract

In this paper, we propose a closed loop system to improve the performance
of single-channel speech separation in a speaker independent
scenario. The system is composed of two interconnected blocks: a
separation block and a speaker identiſcation block. The improvement
is accomplished by incorporating the speaker identities found
by the speaker identiſcation block as additional information for the
separation block, which converts the speaker-independent separation
problem to a speaker-dependent one where the speaker codebooks
are known. Simulation results show that the closed loop system enhances
the quality of the separated output signals. To assess the improvements,
the results are reported in terms of PESQ for both target
and masked signals.
Original languageEnglish
JournalI E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings
Volume2010
Pages (from-to)4430 - 4433
ISSN1520-6149
DOIs
Publication statusPublished - 2010
Event2010 IEEE International Conference on Acoustics, Speech, and Signal Processing - Dallas, United States
Duration: 14 Mar 201017 Mar 2010

Conference

Conference2010 IEEE International Conference on Acoustics, Speech, and Signal Processing
Country/TerritoryUnited States
CityDallas
Period14/03/201017/03/2010

Keywords

  • Single-channel speech separation
  • speaker identification
  • sinusoidal mixture estimator
  • vector quantization
  • Gaussian mixture model

Fingerprint

Dive into the research topics of 'Joint Single-Channel Speech Separation and Speaker Identification'. Together they form a unique fingerprint.

Cite this