| dc.contributor.author | van Niekerk, Daniël R. | |
| dc.contributor.author | Barnard, Etienne | |
| dc.date.accessioned | 2016-05-17T13:55:48Z | |
| dc.date.available | 2016-05-17T13:55:48Z | |
| dc.date.issued | 2014 | |
| dc.identifier.citation | Van Niekerk, D.R. et al. 2014. A target Approximation Intonation Model for Yorùbá TTS (In: 15th Annual Conference of the International Speech Communication Association, Singapore, Hong Kong, September 14-18, 2014. p. 36-40). | en_US |
| dc.identifier.issn | 1990-9770 | |
| dc.identifier.uri | http://hdl.handle.net/10394/17280 | |
| dc.description.abstract | A complete intonation model based on quantitative target approximation is described for Yorùbá text-to-speech (TTS) synthesis. This model is evaluated analytically and perceptually and compared to a fundamental frequency (F0) model using the standard HTS implementation. Analytical results suggest that the proposed approach more efficiently models F0 contours given typical data constraints in under-resourced environments and perceptual results comparing the proposed model with HTS are encouraging. | en_US |
| dc.description.uri | http://www.isca-speech.org/archive/interspeech_2014/ | |
| dc.description.uri | http://www.isca-speech.org/iscaweb/ | |
| dc.language.iso | en | en_US |
| dc.publisher | ISCA | en_US |
| dc.subject | Speech synthesis | en_US |
| dc.subject | Text-to-speech | en_US |
| dc.subject | Intonation model | en_US |
| dc.subject | Target approximation | en_US |
| dc.subject | Tone language | en_US |
| dc.subject | Yorùbá | en_US |
| dc.subject | Underresourced | en_US |
| dc.title | A target Approximation Intonation Model for Yorùbá TTS | en_US |
| dc.type | Presentation | en_US |
| dc.contributor.researchID | 21022658 - Van Niekerk, Daniël Rudolph | |
| dc.contributor.researchID | 21021287 - Barnard, Etienne | |
