Covariance clustering on riemannian manifolds for acoustic model compression

Yusuke Shinohara, Takashi Masuko, Masami Akamine

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

5 Citations (Scopus)

Abstract

A new method of covariance clustering for acoustic model compression is proposed. Since covariance matrices do not form a Euclidean vector space, standard vector clustering algorithms cannot be used effectively for covariance clustering. In this paper, we propose a novel clustering algorithm based on a Riemannian framework, where the covariance space is considered as a Riemannian manifold equipped with the Fisher information metric, and notions of distance and mean are defined on the manifold. The LBG clustering algorithm is naturally extended to the covariance space under the Riemannian framework. Experimental results show the effectiveness of the proposed method, reducing the acoustic model size nearly to the half without noticeable loss in recognition performance.

Original languageEnglish
Title of host publication2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings
Pages4326-4329
Number of pages4
DOIs
Publication statusPublished - 2010 Nov 8
Externally publishedYes
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

  • Acoustic model compression
  • Automatic speech recognition
  • Covariance clustering
  • Fisher information metric
  • Riemannian geometry

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Covariance clustering on riemannian manifolds for acoustic model compression'. Together they form a unique fingerprint.

Cite this