Faster time-aligned phonetic transcriptions through partial automation
DOI:
https://doi.org/10.36505/ExLing-2008/02/0050/000109Keywords:
Brazilian Portuguese, Praat, phonetic transcription, automation toolsAbstract
A semi-automatic process for generating time-aligned transcriptions of speech data at the word and phone level is described. At each stage in the process, segment durations are estimated to generate approximate boundary markers, which are then corrected by hand. Corrections at one level are taken into account in the generation of boundaries for the next level, such that the error is reduced at each successive stage. A test implementation based on Praat was applied to a corpus of Brazilian Portuguese, and a comparison against a fully manual process revealed a reduction of 54% in the time required to generate phonetic transcriptions and an average error of 21 ms in the time-alignment of phonetic boundaries.
References
Barbosa, P. 1995. Estrutura rítmica da frase revelada por aspectos de produção e percepção de fala. Manuscript of talk given at the XLIII Seminário do GEL, May 25-27, 1995, São Paulo, Brazil.
Boersma, P. and Weenink, D. 2008. Praat: doing phonetics by computer (Version 5.0.21). http://www.praat.org/
Silva, D.C., de Lima, A.A., Maia, R., Braga, D., de Moraes, J.F., de Moraes, J.A. and Resende, F.G.V. 2006. A rule-based grapheme-phone converter and stress determination for Brazilian Portuguese natural language processing. Proceedings of the VIth International Telecommunications Symposium (ITS 2006), September 3-6, 2006, Fortaleza, Brazil.
Downloads
Published
Issue
Section
License
Copyright (c) 2008 Ben Serridge (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles are published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are properly credited.
