A Bayesian Approach to Inter-task Fusion for Speaker Recognition

Srikanth R. Madikeri, Petr Motlícek, Subhadeep DeyICASSP 2019 · OpenReview

Abstract

In i-vector based speaker recognition systems, back-end classifiers are trained to factor out nuisance information and retain only the speaker identity. As a result, variabilities arising due to gender, language and accent (among many others) are suppressed. Inter-task fusion, in which such metadata information obtained from automatic systems is used, has been shown to improve speaker recognition performance. In this paper, we explore a Bayesian approach towards inter-task fusion. Speaker similarity score for a test recording is obtained by marginalizing the posterior probability of a speaker. Gender and language probabilities for the test audio are combined with speaker posteriors to obtain a final speaker score. The proposed approach is demonstrated for speaker verification and speaker identification tasks on the NIST SRE 2008 dataset. Relative improvements of up to 10% and 8% are obtained when fusing gender and language information, respectively.
BibTeX
@inproceedings{madikeri2019bayesian,
  author = {Srikanth R. Madikeri and Petr Motlícek and Subhadeep Dey},
  title = {{A Bayesian Approach to Inter-task Fusion for Speaker Recognition}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2019},
  url = {https://openreview.net/forum?id=KOwNXmd9HwU},
}

Loading related content...

Figure