Edinburgh Research Explorer

Phone classification in pseudo-Euclidean Vector Spaces

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

Original languageEnglish
Title of host publicationInterspeech 2004 - ICSLP
Subtitle of host publication8th International Conference on Spoken Language Processing
PublisherInternational Speech Communication Association
Pages1453-1457
Number of pages5
ISBN (Print)ISSN: 1990-9772
Publication statusPublished - 1 Oct 2004

Abstract

Recently we have proposed a structural framework for modelling speech, which is based on patterns of phonological distinctive features, a linguistically well-motivated alternative to standard vector-space acoustic models like HMMs. This framework gives considerable representational freedom by working with features that have explicit linguistic interpretation, but at the expense of the ability to apply the wide range of analytical decision algorithms available in vector spaces, restricting oneself to more computationally expensive and less-developed symbolic metric tools. In this paper we show that a dissimilarity-based distance-preserving transition from the original structural representation to a corresponding pseudo-Euclidean vector space is possible. Promising results of phone classification experiments conducted on the TIMIT database are reported.

ID: 2076841