ISCA Archive Interspeech 2009
ISCA Archive Interspeech 2009

ASR based pronunciation evaluation with automatically generated competing vocabulary

Carlos Molina, Nestor Becerra Yoma, Jorge Wuth, Hiram Vivanco

In this paper the application of automatic speech recognition (ASR) technology in CAPT (Computer Aided Pronunciation Training) is addressed. A method to automatically generate the competitive lexicon, required by an ASR engine to compare the pronunciation of a target word with its correct and wrong phonetic realization, is presented. In order to enable the efficient deployment of CAPT applications, the generation of this competitive lexicon does not require any human assistance or a priori information of mother language dependent errors. The method presented here leads to averaged subjective-objective score correlation equal to 0.82 and 0.75 depending on the task.


doi: 10.21437/Interspeech.2009-552

Cite as: Molina, C., Yoma, N.B., Wuth, J., Vivanco, H. (2009) ASR based pronunciation evaluation with automatically generated competing vocabulary. Proc. Interspeech 2009, 1907-1910, doi: 10.21437/Interspeech.2009-552

@inproceedings{molina09_interspeech,
  author={Carlos Molina and Nestor Becerra Yoma and Jorge Wuth and Hiram Vivanco},
  title={{ASR based pronunciation evaluation with automatically generated competing vocabulary}},
  year=2009,
  booktitle={Proc. Interspeech 2009},
  pages={1907--1910},
  doi={10.21437/Interspeech.2009-552}
}