Automatic Phone Alignment A Comparison between Speaker-Independent Models and Models Trained on the Corpus to Align

Brognaux, Sandrine
(2012) Advances in Natural Language Processing : 8th International Conference on NLP, JapTAL 2012,Proceedings — Vol. 7614, p. 300-311 (2012)

Files

5f9481_0f9f2ab55bbd7d74f6b6449178feb13a.pdf
  • Restricted Access
  • Adobe PDF
  • 307.76 KB
Request a copy

Details

Authors
  • Brognaux, SandrineUCLouvain
    Author
Abstract
Several automatic phonetic alignment tools have been proposed in the literature. They generally use speaker-independent acoustic models of the language to align new corpora. The problem is that the range of provided models is limited. It does not cover all languages and speaking styles (spontaneous, expressive, etc.). This study investigates the possibility of directly training the statistical model on the corpus to align. The main advantage is that it is applicable to any language and speaking style. Moreover, comparisons indicate that it provides as good or better results than using speaker-independent models of the language. It shows that about 2% are gained, with a 20 ms threshold, by using our method. Experiments were carried out on neutral and expressive corpora in French and English. The study also points out that even a small neutral corpus of a few minutes can be exploited to train a model that will provide high-quality alignment.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Brognaux, S. (2012). Automatic Phone Alignment A Comparison between Speaker-Independent Models and Models Trained on the Corpus to Align. Advances in Natural Language Processing : 8th International Conference on NLP, JapTAL 2012,Proceedings, 7614, 300-311. https://hdl.handle.net/2078.5/61165 (Original work published 2012)