Edinburgh Research Explorer

Inductive String Template-Based Learning of Spoken Language

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Related Edinburgh Organisations

Open Access permissions

Open

Documents

Original languageEnglish
Title of host publicationProc. 5th International Workshop on Pattern Recognition in Information Systems (PRIS-2005),
Subtitle of host publicationIn conjunction with the 7th International Conference on Enterprise Information Systems (ICEIS-2005)
EditorsHugo Gamboa, Ana Fred
Place of PublicationMiami, USA
PublisherINSTICC Press
Pages43-51
Number of pages9
Publication statusPublished - 1 May 2005

Abstract

This paper deals with formulation of alternative structural approach to the speech recognition problem. In this approach, we require both the representation and the learning algorithms defined on it to be linguistically meaningful, which allows the speech recognition system to discover the nature of the linguistic classes of speech patterns corresponding to the speech waveforms. We briefly discuss the current formalisms and propose an alternative --- a phonologically inspired string-based inductive speech representation, defined within an analytical framework specifically designed to address the issues of class and object representation. We also present the results of the phoneme classification experiments conducted on the TIMIT corpus of continuous speech.

Download statistics

No data available

ID: 2076657