NWU Institutional Repository

Evaluating acoustic modelling of lexical stress for Afrikaans speech synthesis

Loading...
Thumbnail Image

Date

Authors

Van Niekerk, Daniel R.

Researcher ID

Supervisors

Journal Title

Journal ISSN

Volume Title

Publisher

Pattern Recognition Association of South Africa and Mechatronics International Conference

Record Identifier

Abstract

An explicit lexical stress feature is investigated for statistical parametric speech synthesis in Afrikaans: Firstly, objective measures are used to assess proposed annotation protocols and dictionaries compared to the baseline (implicit modelling) on the Lwazi 2 text-to-speech corpus. Secondly, the best candidates are evaluated on additional corpora. Finally, a comparative subjective evaluation is conducted to determine the perceptual impact on text-to-speech synthesis. The best candidate dictionary is associated with favourable objective results obtained on all corpora and was preferred in the subjective test. This suggests that it may form a basis for further refinement and work on improved prosodic models. Index Terms--pronunciation dictionary, under-resourced language, syllable-stress,

Sustainable Development Goals

Description

Citation

Daniel R. van Niekerk, “Evaluating acoustic modeling of lexical stress for Afrikaans speech synthesis”, in Proc. Annual Symp. Pattern Recognition Association of South Africa and Mechatronics International Conference (PRASA-RobMech), pp 86-91, Bloemfontein, South Africa, 2017. [http://engineering.nwu.ac.za/multilingual-speech-technologies-must/publications]

Endorsement

Review

Supplemented By

Referenced By