Speaker recognition with small training requirements using a combination of VQ and DHMM

Minh Do, Michael Wagner

Research output: Contribution to conferencePaperpeer-review

Abstract

Vector Quantisation (VQ) has been shown to be robust in speaker recognition systems which require a small amount of training data. However the conventional VQ-based method only uses distortion measurements and discards the sequence of quantised codewords. In this paper we propose a method which extends the VQ distortion method by combining it with the likelihood of the sequence of VQ indices against a discrete hidden Markov model (DHMM). The method is particularly suitable for combined speech recognition and speaker recognition systems. Experiments on the TI46 database show that the combined score gives better performance than both the conventional VQ-based and DHMM-based methods.

Original languageEnglish (US)
Pages169-172
Number of pages4
StatePublished - 2020
Externally publishedYes
EventWorkshop on Speaker Recognition and its Commercial and Forensic Applications, RLA2C 1998 - Avignon, France
Duration: Apr 20 1998Apr 23 1998

Conference

ConferenceWorkshop on Speaker Recognition and its Commercial and Forensic Applications, RLA2C 1998
CountryFrance
CityAvignon
Period4/20/984/23/98

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Signal Processing
  • Software

Fingerprint Dive into the research topics of 'Speaker recognition with small training requirements using a combination of VQ and DHMM'. Together they form a unique fingerprint.

Cite this