1 / 19

Rejection of out-of-vocabulary words using phoneme confidence likelihood

Rejection of out-of-vocabulary words using phoneme confidence likelihood. Author: takatoshi jitsuhiro Present: 黃怡寧. Outline. Introduction Rejection by phoneme confidence likelihood Minimum error discriminative training Experiments Conclusion. Introduction.

Download Presentation

Rejection of out-of-vocabulary words using phoneme confidence likelihood

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Rejection of out-of-vocabulary words using phoneme confidence likelihood Author: takatoshi jitsuhiro Present: 黃怡寧

  2. Outline • Introduction • Rejection by phoneme confidence likelihood • Minimum error discriminative training • Experiments • Conclusion

  3. Introduction • Goal: A task independent rejection method that offers high rejection performance.

  4. Rejection by phoneme confidence likelihood • Recognition processing using phoneme confidence likelihood : log of phoneme confidence likelihood : accumulated log likelihood Where is feature vector from time t1 to t2 αis constant

  5. Calculation of confidence likelihood

  6. Definition of phoneme confidence likelihood Where is the log likelihood of the i phoneme model of the candidate for feature of the input voice at time t, and N is the total number of phoneme models, and di=t2-t1 is the duration.

  7. Phoneme confidence likelihood Where a and b are constant. • is taken between 0 and 1. • It approaches 1 when the likelihood of the current phoneme model is relatively larger than of other phoneme models.

  8. Log of sigmoid functiony = -log[1+exp{-a(x+b)}]

  9. Use past records of confidence likelihood Where is the j-th past record of the i-th phoneme, and M is the number of records. • The record of confidence likelihood is not used when M=0.

  10. Minimum error discriminative training (MCE) • : parameter set • : discriminant function • : misclassification function • K: number of competition candidates • η: constant

  11. The class loss function • β and γ: constants • : a small positive real number • Vt: a positive definite matrix

  12. Experiments

  13. Experimental resulrs • No phoneme confidence likelihood (baseline) • Phoneme confidence likelihood (no past record) • 1 past record • 2 past record

  14. False acceptance rates vs. false rejection rates

  15. Word recognition rates vs. false rejection rates

  16. Equal error rates

  17. Word recognition rates at the equal error rate

  18. Word recognition rates in case of no rejection

  19. Conclusion • The rejection accuracy improvement of unknown words was achieved by introducing the phoneme confidence likelihood at each phoneme during the search process. • The rejection performance was further improved by MCE training algorithm because the phoneme confidence likelihood was • made more accurate by this algorithm.

More Related