Decision tree acoustic models for ASR

Jitendra Ajmera, Masami Akamine

Research output: Contribution to journalConference article

2 Citations (Scopus)

Abstract

This paper presents a summary of our research progress using decision-tree acoustic models (DTAM) for large vocabulary speech recognition. Various configurations of training DTAMs are proposed and evaluated on wall-street journal (WSJ) task. A number of different acoustic and categorical features have been used for this purpose. Various ways of realizing a forest instead of a single tree have been presented and shown to improve recognition accuracy. Although the performance is not shown to be better than Gaussian mixture models (GMMs), several advantages of DTAMs have been highlighted and exploited. These include compactness, computational simplicity and ability to handle unordered information.

Original languageEnglish
Pages (from-to)1403-1406
Number of pages4
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Publication statusPublished - 2009 Nov 26
Externally publishedYes
Event10th Annual Conference of the International Speech Communication Association, INTERSPEECH 2009 - Brighton, United Kingdom
Duration: 2009 Sep 62009 Sep 10

Keywords

  • Decision trees
  • Hidden Markov model (HMM)
  • Speech recognition

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Sensory Systems

Fingerprint Dive into the research topics of 'Decision tree acoustic models for ASR'. Together they form a unique fingerprint.

  • Cite this