Technical aspects of concatenation-based singing voice synthesis

Authors

  • L. A. Z. Brum

Keywords:

singing synthesis, MIDI, TTS

Abstract

This article discusses some technical aspects of the concatenation-based method for digital singing voice synthesis, taking as a reference for case study singing in Brazilian Portuguese language. In order to do it, certain aspects of Portuguese phonetics and its relations with singing acoustics will be presented, so a description of the method itself will be possible. Such method basically consists of a concatenation of
digitally prerecorded phonemes with the application of loops on the sustained vowels according to two main data inputs: MIDI protocol messages and the lyrics of the chosen song in a suitable phonetic notation.

Downloads

Published

2012-05-29

How to Cite

Brum, L. A. Z. (2012). Technical aspects of concatenation-based singing voice synthesis. Scientia Plena, 8(3(a). Retrieved from https://scientiaplena.org.br/sp/article/view/919

Issue

Vol. 8 No. 3(a) (2012): March/Março 2012

Section

Articles

License

Authors who publish with this journal agree to the following terms:

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
  3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work