Efficient speaker recognition using approximated cross entropy (ACE)

Hagai Aronowitz, David Burshtein

Research output: Contribution to journalArticlepeer-review

Abstract

Techniques for efficient speaker recognition are presented. These techniques are based on approximating Gaussian mixture modeling (GMM) likelihood scoring using approximated cross entropy (ACE). Gaussian mixture modeling is used for representing both training and test sessions and is shown to perform speaker recognition and retrieval extremely efficiently without any notable degradation in accuracy compared to classic GMM-based recognition. In addition, a GMM compression algorithm is presented. This algorithm decreases considerably the storage needed for speaker retrieval.

Original languageEnglish
Article number4291589
Pages (from-to)2033-2043
Number of pages11
JournalIEEE Transactions on Audio, Speech and Language Processing
Volume15
Issue number7
DOIs
StatePublished - Sep 2007

Keywords

  • Speaker identification
  • Speaker indexing
  • Speaker recognition
  • Speaker retrieval
  • Speaker verification

Fingerprint

Dive into the research topics of 'Efficient speaker recognition using approximated cross entropy (ACE)'. Together they form a unique fingerprint.

Cite this