Decision tree-based acoustic models for speech recognition

Masami Akamine, Jitendra Ajmera

Research output: Contribution to journalArticlepeer-review

6 Citations (Scopus)

Abstract

This article proposes a new acoustic model using decision trees (DTs) as replacements for Gaussian mixture models (GMM) to compute the observation likelihoods for a given hidden Markov model state in a speech recognition system. DTs have a number of advantageous properties, such as that they do not impose restrictions on the number or types of features, and that they automatically perform feature selection. This article explores and exploits DTs for the purpose of large vocabulary speech recognition. Equal and decoding questions have newly been introduced into DTs to directly model gender- and context-dependent acoustic space. Experimental results for the 5k ARPA wall-street-journal task show that context information significantly improves the performance of DT-based acoustic models as expected. Context-dependent DT-based models are highly compact compared to conventional GMM-based acoustic models. This means that the proposed models have effective data-sharing across various context classes.

Original languageEnglish
Article number10
JournalEurasip Journal on Audio, Speech, and Music Processing
Volume2012
Issue number1
DOIs
Publication statusPublished - 2012
Externally publishedYes

Keywords

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

ASJC Scopus subject areas

  • Acoustics and Ultrasonics
  • Electrical and Electronic Engineering

Fingerprint

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

Cite this