ResearchSpace

Automatic stylization, coding and modelling of intonation in text-to-speech for under-resourced languages

Show simple item record

dc.contributor.author Louw, Johannes A
dc.contributor.author Moodley, Avashlin
dc.date.accessioned 2020-03-21T12:05:40Z
dc.date.available 2020-03-21T12:05:40Z
dc.date.issued 2017-12
dc.identifier.citation Louw, J.A. and Moodley, A. 2017. Automatic stylization, coding and modelling of intonation in text-to-speech for under-resourced languages. PRASA-RobMech International Conference, Bloemfontein, Free State, South Africa, 29 November - 1 December 2017, 6pp. en_US
dc.identifier.isbn 978-1-5386-2314-5
dc.identifier.isbn 978-1-5386-2315-2
dc.identifier.uri http://www.rgems.co.za/Downloads/Events/2017_PRASA-RobMech_Program.pdf
dc.identifier.uri DOI: 10.1109/RoboMech.2017.8261147
dc.identifier.uri https://ieeexplore.ieee.org/document/8261147
dc.identifier.uri http://hdl.handle.net/10204/11372
dc.description Copyright: 2017 IEEE. This is the pre-print version of the work. For access to the full text item, kindly consult the publisher's website. en_US
dc.description.abstract In this paper an automatic method to implicitly model intonation for statistical parametric speech synthesis (SPSS) is presented. The approach is ideally suited to single speaker speech databases as used in text-to-speech (TTS), due to the models being speaker-specific. Fundamental frequency curves are automatically stylized based on the speaker-specific acoustics in the recorded database, requiring no models rooted in linguistic theory, and therefore being well suited to intonation modelling in under-resourced languages. The stylized curves are then coded into abstract pitch labels, which are used as features in the training of the statistical parametric acoustic models. A conditional random field (CRF) model is trained in order to predict the abstract pitch labels from the text for synthesis. The CRF model can be used to predict the abstract pitch labels on the syllable, word and phrase tiers. Objective and subjective results on synthetic voices built from English and isiXhosa speech databases are shown. en_US
dc.language.iso en en_US
dc.publisher IEEE en_US
dc.relation.ispartofseries Worklist;19990
dc.subject Automatic stylization en_US
dc.subject Prosody en_US
dc.subject Speech synthesis en_US
dc.subject Text-to-speech en_US
dc.title Automatic stylization, coding and modelling of intonation in text-to-speech for under-resourced languages en_US
dc.type Conference Presentation en_US
dc.identifier.apacitation Louw, J. A., & Moodley, A. (2017). Automatic stylization, coding and modelling of intonation in text-to-speech for under-resourced languages. IEEE. http://hdl.handle.net/10204/11372 en_ZA
dc.identifier.chicagocitation Louw, Johannes A, and Avashlin Moodley. "Automatic stylization, coding and modelling of intonation in text-to-speech for under-resourced languages." (2017): http://hdl.handle.net/10204/11372 en_ZA
dc.identifier.vancouvercitation Louw JA, Moodley A, Automatic stylization, coding and modelling of intonation in text-to-speech for under-resourced languages; IEEE; 2017. http://hdl.handle.net/10204/11372 . en_ZA
dc.identifier.ris TY - Conference Presentation AU - Louw, Johannes A AU - Moodley, Avashlin AB - In this paper an automatic method to implicitly model intonation for statistical parametric speech synthesis (SPSS) is presented. The approach is ideally suited to single speaker speech databases as used in text-to-speech (TTS), due to the models being speaker-specific. Fundamental frequency curves are automatically stylized based on the speaker-specific acoustics in the recorded database, requiring no models rooted in linguistic theory, and therefore being well suited to intonation modelling in under-resourced languages. The stylized curves are then coded into abstract pitch labels, which are used as features in the training of the statistical parametric acoustic models. A conditional random field (CRF) model is trained in order to predict the abstract pitch labels from the text for synthesis. The CRF model can be used to predict the abstract pitch labels on the syllable, word and phrase tiers. Objective and subjective results on synthetic voices built from English and isiXhosa speech databases are shown. DA - 2017-12 DB - ResearchSpace DP - CSIR KW - Automatic stylization KW - Prosody KW - Speech synthesis KW - Text-to-speech LK - https://researchspace.csir.co.za PY - 2017 SM - 978-1-5386-2314-5 SM - 978-1-5386-2315-2 T1 - Automatic stylization, coding and modelling of intonation in text-to-speech for under-resourced languages TI - Automatic stylization, coding and modelling of intonation in text-to-speech for under-resourced languages UR - http://hdl.handle.net/10204/11372 ER - en_ZA


Files in this item

This item appears in the following Collection(s)

Show simple item record