ISCA Archive Eurospeech 1999
ISCA Archive Eurospeech 1999

Automatic detection of phone-level mispronunciation for language learning

Horacio Franco, Leonardo Neumeyer, María Ramos, Harry Bratt

We are interested in automatically detecting specific phone seg-ments that have been mispronounced by a nonnative student of a foreign language. The phone-level information allows a language instruction system to provide the student with feedback about specific pronunciation mistakes. Two approaches were evaluated; in the first approach, log-posterior probability-based scores [1] are computed for each phone segment. These probabilities are based on acoustic models of native speech. The sec-ond approach uses a phonetically labeled nonnative speech database to train two different acoustic models for each phone: one model is trained with the acceptable, or correct native-like pronunciations, while the other model is trained with the incorrect, strongly nonnative pronunciations. For each phone seg-ment, a log-likelihood ratio score is computed using the incorrect and correct pronunciation models. Either type of score is compared with a phone dependent threshold to detect a mispronunciation. Performance of both approaches was evaluated in a phonetically transcribed database of 130,000 phones uttered in continuous speech sentences by 206 nonnative speakers.


doi: 10.21437/Eurospeech.1999-207

Cite as: Franco, H., Neumeyer, L., Ramos, M., Bratt, H. (1999) Automatic detection of phone-level mispronunciation for language learning. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 851-854, doi: 10.21437/Eurospeech.1999-207

@inproceedings{franco99_eurospeech,
  author={Horacio Franco and Leonardo Neumeyer and María Ramos and Harry Bratt},
  title={{Automatic detection of phone-level mispronunciation for language learning}},
  year=1999,
  booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
  pages={851--854},
  doi={10.21437/Eurospeech.1999-207}
}