Repository logo
 
Publication

Use of phoneme dedicated artificial neural networks to predict segmental durations

dc.contributor.authorTeixeira, João Paulo
dc.contributor.authorFreitas, Diamantino Silva
dc.date.accessioned2010-02-11T20:29:08Z
dc.date.available2010-02-11T20:29:08Z
dc.date.issued2005
dc.description.abstractThe results of two alternative models to predict segmental durations in speech synthesis, both based on Artificial Neural Networks (ANNs) are discussed. The ANN model consists in just one ANN trained to predict the segmental durations for all phonemes. The phoneme dedicated ANN model consists in a set of ANNs, each one dedicated to predict the segmental duration of a specific phoneme. Both models are compared with the same input information extracted from one European Portuguese database. Objective and subjective measurements of performance of both approaches are compared. A slight preference was denoted for the phoneme dedicated ANN model.pt
dc.identifier.citationTeixeira, João Paulo; Freitas, D. (2005). Use of phoneme dedicated artificial neural networks to predict segmental durations. In 10th International Conference on Speech and Computer. Patras, Greece. 9, p.679-682.pt
dc.identifier.issn1018-4074
dc.identifier.urihttp://hdl.handle.net/10198/1861
dc.language.isoengpt
dc.publisherUniversity of Patraspt
dc.titleUse of phoneme dedicated artificial neural networks to predict segmental durationspt
dc.typeconference paper
dspace.entity.typePublication
oaire.citation.conferencePlacePatras, Greece.pt
oaire.citation.endPage682pt
oaire.citation.issue9pt
oaire.citation.startPage679pt
oaire.citation.title10th International Conference on Speech and Computerpt
person.familyNameTeixeira
person.givenNameJoão Paulo
person.identifier663194
person.identifier.ciencia-id4F15-B322-59B4
person.identifier.orcid0000-0002-6679-5702
person.identifier.ridN-6576-2013
person.identifier.scopus-author-id57069567500
rcaap.rightsopenAccesspt
rcaap.typeconferenceObjectpt
relation.isAuthorOfPublication33f4af65-7ddf-46f0-8b44-a7470a8ba2bf
relation.isAuthorOfPublication.latestForDiscovery33f4af65-7ddf-46f0-8b44-a7470a8ba2bf

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
dur_eurospeech_05_ver3.pdf
Size:
219.19 KB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.83 KB
Format:
Item-specific license agreed upon to submission
Description: