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

Masami Akamine, Jitendra Ajmera

Research output: Contribution to journalArticlepeer-review

Abstract

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.

Original languageEnglish
Pages (from-to)2250-2258
Number of pages9
JournalIEICE Transactions on Information and Systems
VolumeE94-D
Issue number11
DOIs
Publication statusPublished - 2011 Nov

Keywords

  • Acoustic modeling
  • Decision trees
  • Likelihood computation
  • Probability estimation
  • Speech recognition

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Decision tree-based acoustic models for speech recognition with improved smoothness'. Together they form a unique fingerprint.

Cite this