Aspect-model-based reference speaker weighting

Seongjun Hahm, Yuichi Ohkawa, Masashi Ito, Motoyuki Suzuki, Akinori Ito, Shozo Makino

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

6 Citations (Scopus)

Abstract

We propose an aspect-model-based reference speaker weighting. The main idea of the approach is that the adapted model is a linear combination of a set of reference speakers like reference speaker weighting (RSW) and eigenvoices. The aspect model is the mixture model of speaker-dependent (SD) models. In this paper, aspect model weighting (AMW) is proposed for finding an optimal weighting of a set of reference speakers unlike RSW and the aspect model which is a kind of cluster models is trained based on likelihood maximization with respect to the training data. The number of adaptation parameters can also be reduced using aspect model approach. For evaluation, we carried out an isolated word recognition experiment on Korean database (KLE452). The results were compared to those of conventional MAP, MLLR, RSW, and eigenvoice. Even though we use only 0.5s of adaptation data, 27.24% relative error rate reduction in comparison with speaker-independent (SI) baseline performance was achieved.

Original languageEnglish
Title of host publication2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings
Pages4302-4305
Number of pages4
DOIs
Publication statusPublished - 2010 Nov 8
Event2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Dallas, TX, United States
Duration: 2010 Mar 142010 Mar 19

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149

Other

Other2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010
CountryUnited States
CityDallas, TX
Period10/3/1410/3/19

Keywords

  • Aspect model weighting
  • Reference speaker weighting
  • Speaker adaptation
  • Speech recognition

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Aspect-model-based reference speaker weighting'. Together they form a unique fingerprint.

Cite this