Decision tree-based acoustic models for speech recognition with improved smoothness

Masami Akamine, Jitendra Ajmera

研究成果: Article査読

抄録

This paper proposes likelihood smoothing techniques to improve decision tree-based acoustic models, where decision trees are used as replacements for Gaussian mixture models to compute the observation likelihoods for a given HMM state in a speech recognition system. Decision trees have a number of advantageous properties, such as not imposing restrictions on the number or types of features, and automatically performing feature selection. This paper describes basic configurations of decision tree-based acoustic models and proposes two methods to improve the robustness of the basic model: DT mixture models and soft decisions for continuous features. Experimental results for the Aurora 2 speech database show that a system using decision trees offers state-of-the-art performance, even without taking advantage of its full potential and soft decisions improve the performance of DT-based acoustic models with 16.8% relative error rate reduction over hard decisions.

本文言語English
ページ(範囲)2250-2258
ページ数9
ジャーナルIEICE Transactions on Information and Systems
E94-D
11
DOI
出版ステータスPublished - 2011 11月
外部発表はい

ASJC Scopus subject areas

  • ソフトウェア
  • ハードウェアとアーキテクチャ
  • コンピュータ ビジョンおよびパターン認識
  • 電子工学および電気工学
  • 人工知能

フィンガープリント

「Decision tree-based acoustic models for speech recognition with improved smoothness」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