A new method for mispronunciation detection using Support Vector Machine based on Pronunciation Space Models

@article{Wei2009ANM,
  title={A new method for mispronunciation detection using Support Vector Machine based on Pronunciation Space Models},
  author={Si Wei and Guoping Hu and Yu Hu and Ren-Hua Wang},
  journal={Speech Communication},
  year={2009},
  volume={51},
  pages={896-905}
}
This paper presents two new ideas for text dependent mispronunciation detection. Firstly, mispronunciation detection is formulated as a classification problem to integrate various predictive features. A Support Vector Machine (SVM) is used as the classifier and the loglikelihood ratios between all the acoustic models and the model corresponding to the given text are employed as features for the classifier. Secondly, Pronunciation Space Models (PSMs) are proposed to enhance the discriminative… CONTINUE READING
BETA

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • The overall recall rates for the 13 most frequently mispronounced phones increase from 17.2%, 7.6% and 0% to 58.3%, 44.3% and 29.5% at three precision levels of 60%, 70% and 80%, respectively.

Citations

Publications citing this paper.
SHOWING 1-10 OF 49 CITATIONS

Automatic Assessment of English as a Second Language

VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Maximum F1-Score Discriminative Training Criterion for Automatic Mispronunciation Detection

  • IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • 2015
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Supervised Detection and Unsupervised Discovery of Pronunciation Error Patterns for Computer-Assisted Language Learning

  • IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • 2015
VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Automatic detection of unnatural word-level segments in unit-selection speech synthesis

  • 2011 IEEE Workshop on Automatic Speech Recognition & Understanding
  • 2011
VIEW 7 EXCERPTS
CITES BACKGROUND & RESULTS
HIGHLY INFLUENCED

PCA Method for Automated Detection of Mispronounced Words

  • Defense + Commercial Sensing
  • 2011
VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 25 REFERENCES

Pronunciation modeling for spontaneous Mandarin speech recognition

Y. Liu
  • Ph.D. Thesis,
  • 2002
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Automatic detection of phone-level mispronunciation for language learning

H. Franco, L. Neumeyer, Y. Kim, O. Ronen, H. Bratt
  • Proc. European Conference on Speech Communication and Technology,
  • 1999
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Automatic mispronunciation detection for Mandarin

  • 2008 IEEE International Conference on Acoustics, Speech and Signal Processing
  • 2008
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…