Multi-path, context dependent SC-HMM architectures for improved connected word recognition

Tzur Vaich, Anion Cohen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Connected Word Recognition (CWR) systems are needed for many consumer applications. In such applications cost is a major factor. Several architectures for HMM based CWR are examined to provide an optimal cost effective configuration. Three architectures were examined: a simple LTR with no skips, LTR with skips (LTR-WS) and Multi-Path LTR. The LTR-WS and the MP-LTR were shown to be superior to the simple LTR. The MP-LTR exhibited the best results with long strings.

Original languageEnglish
Title of host publication6th International Conference on Spoken Language Processing, ICSLP 2000
PublisherInternational Speech Communication Association
ISBN (Electronic)7801501144, 9787801501141
StatePublished - 1 Jan 2000
Externally publishedYes
Event6th International Conference on Spoken Language Processing, ICSLP 2000 - Beijing, China
Duration: 16 Oct 200020 Oct 2000

Publication series

Name6th International Conference on Spoken Language Processing, ICSLP 2000

Conference

Conference6th International Conference on Spoken Language Processing, ICSLP 2000
Country/TerritoryChina
CityBeijing
Period16/10/0020/10/00

ASJC Scopus subject areas

  • Linguistics and Language
  • Language and Linguistics

Fingerprint

Dive into the research topics of 'Multi-path, context dependent SC-HMM architectures for improved connected word recognition'. Together they form a unique fingerprint.

Cite this