Feature-space structural MAPLR with regression tree-based multiple transformation matrices for DNN

Hiroki Kanagawa, Yuuki Tachioka, Shinji Watanabe, Jun Ishii

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

Feature-space maximum-likelihood linear regression (fMLLR) transforms acoustic features to adapted ones by a multiplication operation with a single transformation matrix. This property realizes an efficient adaptation performed within a pre-precessing, which is independent of a decoding process, and this type of adaptation can be applied to deep neural network (DNN). On the other hand, constrained MLLR (CMLLR) uses multiple transformation matrices based on a regression tree, which provides further improvement from fMLLR. However, there are two problems in the model-space adaptations: first, these types of adaptation cannot be applied to DNN because adaptation and decoding must share the same generative model, i.e. Gaussian mixture model (GMM). Second, transformation matrices tend to be overly fit when the amount of adaptation data is small. This paper proposes to use multiple transformation matrices within a feature-space adaptation framework. The proposed method first estimates multiple transformation matrices in the GMM framework according to the first-pass decoding results and the alignments, and then takes a weighted sum of these matrices to obtain a single feature transformation matrix frame-by-frame. In addition, to address the second problem, we propose feature-space structural maximum a posteriori linear regression (fSMAPLR), which introduces hierarchal prior distributions to regularize the MAP estimation. Experimental results show that the proposed fSMAPLR outperformed fMLLR.

本文言語English
ホスト出版物のタイトル2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015
出版社Institute of Electrical and Electronics Engineers Inc.
ページ86-92
ページ数7
ISBN(電子版)9789881476807
DOI
出版ステータスPublished - 2016 2月 19
外部発表はい
イベント2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015 - Hong Kong, Hong Kong
継続期間: 2015 12月 162015 12月 19

Other

Other2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015
国/地域Hong Kong
CityHong Kong
Period15/12/1615/12/19

ASJC Scopus subject areas

  • 人工知能
  • モデリングとシミュレーション
  • 信号処理

フィンガープリント

「Feature-space structural MAPLR with regression tree-based multiple transformation matrices for DNN」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