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 |