Feature enhancement with joint use of consecutive corrupted and noise feature vectors with discriminative region weighting

Masayuki Suzuki, Takuya Yoshioka, Shinji Watanabe, Nobuaki Minematsu, Keikichi Hirose

研究成果: Article

3 引用 (Scopus)

抜粋

This paper proposes a feature enhancement method that can achieve high speech recognition performance in a variety of noise environments with feasible computational cost. As the well-known Stereo-based Piecewise Linear Compensation for Environments (SPLICE) algorithm, the proposed method learns piecewise linear transformation to map corrupted feature vectors to the corresponding clean features, which enables efficient operation. To make the feature enhancement process adaptive to changes in noise, the piecewise linear transformation is performed by using a subspace of the joint space of corrupted and noise feature vectors, where the subspace is chosen such that classes (i.e., Gaussian mixture components) of underlying clean feature vectors can be best predicted. In addition, we propose utilizing temporally adjacent frames of corrupted and noise features in order to leverage dynamic characteristics of feature vectors. To prevent overfitting caused by the high dimensionality of the extended feature vectors covering the neighboring frames, we introduce regularized weighted minimum mean square error criterion. The proposed method achieved relative improvements of 34.2% and 22.2% over SPLICE under the clean and multi-style conditions, respectively, on the Aurora 2 task.

元の言語English
記事番号6544587
ページ(範囲)2172-2181
ページ数10
ジャーナルIEEE Transactions on Audio, Speech and Language Processing
21
発行部数10
DOI
出版物ステータスPublished - 2013 8 8
外部発表Yes

ASJC Scopus subject areas

  • Acoustics and Ultrasonics
  • Electrical and Electronic Engineering

フィンガープリント Feature enhancement with joint use of consecutive corrupted and noise feature vectors with discriminative region weighting' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用