Van Niekerk, DRBarnard, E2010-12-132010-12-132010-09Van Niekerk, DR and Barnard, E. 2010. Intonation model for TTS in Sepedi. International Speech Communication Association (Interspeech), Makuhari, Japan, 26 - 30 September 2010, pp 41990-9772http://hdl.handle.net/10204/4661International Speech Communication Association (Interspeech), Makuhari, Japan, 26 - 30 September 2010The authors present an initial investigation into the acoustic realisation of tone in continuous utterances in Sepedi (a language in the Southern Bantu family). An analytic model for the generation of appropriate pitch contours given an utterance with linguistic tone specification is presented and evaluated. By comparing the model output to speech data from a small tone-marked corpus we conclude that the initial implementation presented here is capable of generating pitch contours exhibiting some realistic properties and identify a number of aspects that require further attention. Lastly, we present some initial perceptual results when integrating the proposed model into a Hidden Markov Model-based speech synthesis system.enSpeech synthesisTone languagesSepediSpeech communicationInterspeech 2010Conference PresentationVan Niekerk, D., & Barnard, E. (2010). Intonation model for TTS in Sepedi. INTERSPEECH 2010. http://hdl.handle.net/10204/4661Van Niekerk, DR, and E Barnard. "Intonation model for TTS in Sepedi." (2010): http://hdl.handle.net/10204/4661Van Niekerk D, Barnard E, Intonation model for TTS in Sepedi; INTERSPEECH 2010; 2010. http://hdl.handle.net/10204/4661 .TY - Conference Presentation AU - Van Niekerk, DR AU - Barnard, E AB - The authors present an initial investigation into the acoustic realisation of tone in continuous utterances in Sepedi (a language in the Southern Bantu family). An analytic model for the generation of appropriate pitch contours given an utterance with linguistic tone specification is presented and evaluated. By comparing the model output to speech data from a small tone-marked corpus we conclude that the initial implementation presented here is capable of generating pitch contours exhibiting some realistic properties and identify a number of aspects that require further attention. Lastly, we present some initial perceptual results when integrating the proposed model into a Hidden Markov Model-based speech synthesis system. DA - 2010-09 DB - ResearchSpace DP - CSIR KW - Speech synthesis KW - Tone languages KW - Sepedi KW - Speech communication KW - Interspeech 2010 LK - https://researchspace.csir.co.za PY - 2010 SM - 1990-9772 T1 - Intonation model for TTS in Sepedi TI - Intonation model for TTS in Sepedi UR - http://hdl.handle.net/10204/4661 ER -