ResearchSpace

Predicting utterance pitch targets in Yoruba for tone realisation in speech synthesis

Show simple item record

dc.contributor.author Van Niekerk, DR
dc.contributor.author Barnard, E
dc.date.accessioned 2013-08-12T06:27:15Z
dc.date.available 2013-08-12T06:27:15Z
dc.date.issued 2013
dc.identifier.citation Van Niekerk, D.R and Barnard, E. 2013. V. Predicting utterance pitch targets in Yoruba for tone realisation in speech synthesis. Speech Communication, pp 1-14 en_US
dc.identifier.issn 0167-6393
dc.identifier.uri http://www.sciencedirect.com/science/article/pii/S0167639313000125
dc.identifier.uri http://hdl.handle.net/10204/6934
dc.description Copyright: 2013 Elsevier. This is the post print version. The definitive version is published in Speech Communication, pp 1-14 en_US
dc.description.abstract Pitch is a fundamental acoustic feature of speech and as such needs to be determined during the process of speech synthesis. While a range of communicative functions are attributed to pitch variation in speech of all languages, it plays a vital role in distinguishing meaning of lexical items in tone languages. As a number of factors are assumed to affect the realisation of pitch, it is important to know which mechanisms are systematically responsible for pitch realisation in order to be able to model these effectively and thus develop robust speech synthesis systems in under-resourced environments. To this end, features influencing syllable pitch targets in continuous utterances in Yoruba are investigated in a small speech corpus of 4 speakers. It is found that the previous syllable pitch level is strongly correlated with pitch changes between syllables and a number of approaches and features are evaluated in this context. The resulting models can be used to predict utterance pitch targets for speech synthesisers (whether it be concatenative or statistical parametric systems), and may also prove useful in speech-recognition systems. en_US
dc.language.iso en en_US
dc.publisher Elsevier en_US
dc.relation.ispartofseries Workflow;11357
dc.subject Yoruba en_US
dc.subject Tone language en_US
dc.subject Speech synthesis en_US
dc.subject Fundamental frequency en_US
dc.title Predicting utterance pitch targets in Yoruba for tone realisation in speech synthesis en_US
dc.type Article en_US
dc.identifier.apacitation Van Niekerk, D., & Barnard, E. (2013). Predicting utterance pitch targets in Yoruba for tone realisation in speech synthesis. http://hdl.handle.net/10204/6934 en_ZA
dc.identifier.chicagocitation Van Niekerk, DR, and E Barnard "Predicting utterance pitch targets in Yoruba for tone realisation in speech synthesis." (2013) http://hdl.handle.net/10204/6934 en_ZA
dc.identifier.vancouvercitation Van Niekerk D, Barnard E. Predicting utterance pitch targets in Yoruba for tone realisation in speech synthesis. 2013; http://hdl.handle.net/10204/6934. en_ZA
dc.identifier.ris TY - Article AU - Van Niekerk, DR AU - Barnard, E AB - Pitch is a fundamental acoustic feature of speech and as such needs to be determined during the process of speech synthesis. While a range of communicative functions are attributed to pitch variation in speech of all languages, it plays a vital role in distinguishing meaning of lexical items in tone languages. As a number of factors are assumed to affect the realisation of pitch, it is important to know which mechanisms are systematically responsible for pitch realisation in order to be able to model these effectively and thus develop robust speech synthesis systems in under-resourced environments. To this end, features influencing syllable pitch targets in continuous utterances in Yoruba are investigated in a small speech corpus of 4 speakers. It is found that the previous syllable pitch level is strongly correlated with pitch changes between syllables and a number of approaches and features are evaluated in this context. The resulting models can be used to predict utterance pitch targets for speech synthesisers (whether it be concatenative or statistical parametric systems), and may also prove useful in speech-recognition systems. DA - 2013 DB - ResearchSpace DP - CSIR KW - Yoruba KW - Tone language KW - Speech synthesis KW - Fundamental frequency LK - https://researchspace.csir.co.za PY - 2013 SM - 0167-6393 T1 - Predicting utterance pitch targets in Yoruba for tone realisation in speech synthesis TI - Predicting utterance pitch targets in Yoruba for tone realisation in speech synthesis UR - http://hdl.handle.net/10204/6934 ER - en_ZA


Files in this item

This item appears in the following Collection(s)

Show simple item record