Evaluation of the Vocal Tract Length Normalization Based Classifiers for Speaker Verification

Authors

  • Walid Hussein Faculty of Informatics and Computer Science, The British University in Egypt
  • Sarah Akram Essmat Faculty of Informatics and Computer Science, The British University in Egypt
  • Nestor Yoma Universidad de Chile
  • Fernando Huenupán Universidad de La Frontera, Chile

DOI:

https://doi.org/10.3991/ijes.v4i4.6544

Abstract


This paper proposes and evaluates classifiers based on Vocal Tract Length Normalization (VTLN) in a text-dependent speaker verification (SV) task with short testing utterances. This type of tasks is important in commercial applications and is not easily addressed with methods designed for long utterances such as JFA and i-Vectors. In contrast, VTLN is a speaker compensation scheme that can lead to significant improvements in speech recognition accuracy with just a few seconds of speech samples. A novel scheme to generate new classifiers is employed by incorporating the observation vector sequence compensated with VTLN. The modified sequence of feature vectors and the corresponding warping factors are used to generate classifiers whose scores are combined by a Support Vector Machine (SVM) based SV system. The proposed scheme can provide an average reduction in EER equal to 14% when compared with the baseline system based on the likelihood of observation vectors.

Downloads

Published

2016-12-30

How to Cite

Hussein, W., Essmat, S. A., Yoma, N., & Huenupán, F. (2016). Evaluation of the Vocal Tract Length Normalization Based Classifiers for Speaker Verification. International Journal of Recent Contributions from Engineering, Science & IT (iJES), 4(4), pp. 41–44. https://doi.org/10.3991/ijes.v4i4.6544

Issue

Section

Papers