Loading...

Speaker recognition with random digit strings using uncertainty normalized HMM-Based i-Vectors

Maghsoodi, N ; Sharif University of Technology | 2019

430 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/TASLP.2019.2928143
  3. Publisher: Institute of Electrical and Electronics Engineers Inc , 2019
  4. Abstract:
  5. In this paper, we combine Hidden Markov Models HMMs with i-vector extractors to address the problem of text-dependent speaker recognition with random digit strings. We employ digit-specific HMMs to segment the utterances into digits, to perform frame alignment to HMM states and to extract Baum-Welch statistics. By making use of the natural partition of input features into digits, we train digit-specific i-vector extractors on top of each HMM and we extract well-localized i-vectors, each modelling merely the phonetic content corresponding to a single digit. We then examine ways to perform channel and uncertainty compensation, and we propose a novel method for using the uncertainty in the i-vector estimates. The experiments on RSR2015 part III show that the proposed method attains 1.52 and 1.77 Equal Error Rate EER for male and female respectively, outperforming state-of-the-art methods such as x-vectors, trained on vast amounts of data. Furthermore, these results are attained by a single system trained entirely on RSR2015, and by a simple score-normalized cosine distance. Moreover, we show that the omission of channel compensation yields only a minor degradation in performance, meaning that the system attains state-of-the-art results even without recordings from multiple handsets per speaker for training or enrolment. Similar conclusions are drawn from our experiments on the RedDots corpus, where the same method is evaluated on phrases. Finally, we report results with bottleneck features and show that further improvement is attained when fusing them with spectral features. © 2019 Institute of Electrical and Electronics Engineers Inc.. All rights reserved
  6. Keywords:
  7. HMM ; Text dependent speaker verification ; Text-prompted ; Uncertainty compensation ; Character recognition ; Speech analysis ; Speech recognition ; Uncertainty analysis ; Vectors ; Bottleneck features ; Channel compensation ; Normalized cosine distances ; Speaker recognition ; Speaker verification ; State of the art ; State-of-the-art methods ; Hidden Markov models
  8. Source: IEEE/ACM Transactions on Audio Speech and Language Processing ; Volume 27, Issue 11 , 2019 , Pages 1815-1825 ; 23299290 (ISSN)
  9. URL: https://ieeexplore.ieee.org/document/8759963