Show simple item record

dc.contributor.authorKing, Simon
dc.contributor.authorStephenson, Todd
dc.contributor.authorIsard, Stephen
dc.contributor.authorTaylor, Paul
dc.contributor.authorStrachan, Alex
dc.coverage.spatial4en
dc.date.accessioned2006-05-11T16:51:17Z
dc.date.available2006-05-11T16:51:17Z
dc.date.issued1998-12
dc.identifier.citationIn ICSLP-1998, paper 0557en
dc.identifier.urihttp://www.isca-speech.org/archive/icslp_1998/index.html
dc.identifier.urihttp://hdl.handle.net/1842/1004
dc.description.abstractWe describe a speech recogniser which uses a speech production-motivated phonetic-feature description of speech. We argue that this is a natural way to describe the speech signal and offers an efficient intermediate parameterisation for use in speech recognition. We also propose to model this description at the syllable rather than phone level. The ultimate goal of this work is to generate syllable models whose parameters explicitly describe the trajectories of the phonetic features of the syllable. We hope to move away from Hidden Markov Models (HMMs) of context-dependent phone units. As a step towards this, we present a preliminary system which consists of two parts: recognition of the phonetic features from the speech signal using a neural network; and decoding of the feature-based description into phonemes using HMMs.en
dc.format.extent166980 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherInternational Speech Communication Associationen
dc.titleSpeech Recognition Via Phonetically Featured Syllablesen
dc.typeConference Paperen


Files in this item

This item appears in the following Collection(s)

Show simple item record