dc.contributor.author |
Van Heerden, C.J.
|
|
dc.contributor.author |
Barnard, E.
|
|
dc.date.accessioned |
2008-08-27T05:49:57Z |
|
dc.date.available |
2008-08-27T05:49:57Z |
|
dc.date.issued |
2008-06 |
|
dc.description.abstract |
The durations of phonemes varies for different speakers. To this end, the correlations between phonemes across different speakers are studied and a novel approach to predict unknown phoneme durations from the values of known phoneme durations for a particular speaker are presented, based on the maximum likelihood criterion. Several interesting patterns are observed. Phonemes from the same broad phonetic class tend to covary most strongly (and therefore intra-class predictions of unknown phoneme durations are most accurate), but significant cross-class correlations are also present. Consequently, knowledge of only a few highly-correlated phonemes’ durations is necessary to make a good duration prediction. |
en |
dc.format.extent |
295205 bytes |
|
dc.format.mimetype |
application/pdf |
|
dc.identifier.citation |
Van Heerden, CJ & Barnard, E 2008, 'Speaker-specific variability of phoneme durations', South African Computer Journal, no.40, pp.44-50. [http://www.journals.co.za/ej/ejour_comp.html] |
en |
dc.identifier.issn |
1015-7999 |
|
dc.identifier.uri |
http://hdl.handle.net/2263/6751 |
|
dc.language.iso |
en |
en |
dc.publisher |
Computer Society of South Africa |
en |
dc.rights |
Computer Society of South Africa |
en |
dc.subject |
Phoneme durations |
en |
dc.subject |
Speech recognition |
en |
dc.subject |
Maximum likelihood |
en |
dc.subject |
Eigenvectors |
en |
dc.subject.lcsh |
Phonemics |
|
dc.subject.lcsh |
Automatic speech recognition |
|
dc.title |
Speaker-specific variability of phoneme durations |
en |
dc.type |
Article |
en |