Acoustic model adaptation based on coarse/fine training of transfer vectors using directional statistics

Shinji Watanabe*, Atsushi Nakamura

*この研究の対応する著者

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

In this paper, we reformulate an adaptation scheme of Coarse/Fine Training (CFT) of transfer vectors in acoustic modeling by using directional statistics. In CFT, the transfer vector is decomposed into a unit direction vector and a scaling factor. By using coarse tied Gaussian class (coarse class) estimation for the unit direction vector, and by using fine tied Gaussian class (fine class) estimation for the scaling factor, we can obtain accurate transfer vectors with a small number of free parameters. Directional statistics is a method for analyzing geometric parameters (e.g. angle and unit vector) using directional data, and is suited for the analysis of the CFT representation. Using directional statistics as a basis, we construct expectation-maximization algorithms for CFT parameters an-alytically using the maximum likelihood and Bayesian (maximum a posteriori) approaches. In particular, with the Bayesian approach, prior and posterior distributions for unit direction vectors are represented with a von Mises distribution, a representative distribution in directional statistics. Speaker adaptation experiments show that our proposal improves the performance of large vocabulary continuous speech recognition due to the efficient coarse/fine representation of transfer vectors, compared with the conventional transfer vector adaptation.

本文言語English
ホスト出版物のタイトル2006 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings
ページI1005-I1008
出版ステータスPublished - 2006 12月 1
外部発表はい
イベント2006 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2006 - Toulouse, France
継続期間: 2006 5月 142006 5月 19

出版物シリーズ

名前ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
1
ISSN(印刷版)1520-6149

Conference

Conference2006 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2006
国/地域France
CityToulouse
Period06/5/1406/5/19

ASJC Scopus subject areas

  • ソフトウェア
  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「Acoustic model adaptation based on coarse/fine training of transfer vectors using directional statistics」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル