Edinburgh Research Explorer

Speech production knowledge in automatic speech recognition

Research output: Contribution to journalArticle

Related Edinburgh Organisations

Open Access permissions

Open

Documents

Original languageEnglish
Pages (from-to)723-742
Number of pages20
JournalJournal of the acoustical society of america
Volume121
Issue number2
DOIs
Publication statusPublished - 1 Feb 2007

Abstract

Although much is known about how speech is produced, and research into speech production has resulted in measured articulatory data, feature systems of different kinds and numerous models, speech production knowledge is almost totally ignored in current mainstream approaches to automatic speech recognition. Representations of speech production allow simple explanations for many phenomena observed in speech which cannot be easily analyzed from either acoustic signal or phonetic transcription alone. In this article, we provide a survey of a growing body of work in which such representations are used to improve automatic speech recognition.

Download statistics

No data available

ID: 2077792