Improving a tone labeling algorithm for Sesotho.
We report on a study that aimed to improve an existing tone label prediction algorithm for Sesotho, an official language of South Africa. Tone is an important prosodic feature of Sesotho, since speakers use tone to distinguish meaning. In order to implement tone in a Text-to-Speech system for Sesoth...
| Publicado en: | Language Resources & Evaluation Vol. 49; no. 1; pp. 19 - 51 |
|---|---|
| Autores principales: | , , |
| Formato: | Artículo |
| Publicado: |
Springer Nature
Mar2015
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=101004169&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 101004169 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 1574020X 179V jtl: Language Resources & Evaluation issn: 1574020X maglogo: N pubinfo: dt: Mar2015 vid: 49 iid: 1 pid: 237 pub: Springer Nature artinfo: ui: 101004169 10.1007/s10579-014-9281-4 ppf: 19 ppct: 32 formats: fmt: @attributes: type: P size: 403KB tig: atl: Improving a tone labeling algorithm for Sesotho. aug: au: Raborife, Mpho Ewert, Sigrid Zerbian, Sabine affil: School of Computer Science, University of the Witwatersrand, Johannesburg South Africa Institute of Linguistics: English, University of Stuttgart, Stuttgart Germany su: Sotho language Linguistics Speech processing systems Orthography & spelling Computer science South Africa sug: subj: South Africa Sotho language Linguistics Speech processing systems Orthography & spelling Computer science keyword: Algorithm Bantu languages Sesotho Text-to-Speech systems Tone ab: We report on a study that aimed to improve an existing tone label prediction algorithm for Sesotho, an official language of South Africa. Tone is an important prosodic feature of Sesotho, since speakers use tone to distinguish meaning. In order to implement tone in a Text-to-Speech system for Sesotho, a tone modeling algorithm must receive as input the tone labels of the syllables of each word. Then it can predict the appropriate intonation of the word. Since Sesotho does not mark tone labels in orthography, the labels have to be predicted according to the tonal rules of the language. The existing tone label prediction algorithm has two drawbacks, namely it implements three tonal rules only and is restricted to the clitic phrase domain. In our study, we developed an algorithm that implements four additional tonal rules and addresses all parts of speech. The results show that the latter algorithm significantly improves the existing one by increasing the number of matched tone labels. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y custom: Language Resources & Evaluation is a copyright of Springer, 2015. All Rights Reserved. item: Language Resources & Evaluation holder: Springer Nature dt: @attributes: year: 2015 holdings: @attributes: islocal: N |
|---|