English

Improved Vocal Effort Transfer Vector Estimation for Vocal Effort-Robust Speaker Verification

Audio and Speech Processing 2023-07-06 v3 Human-Computer Interaction

Abstract

Despite the maturity of modern speaker verification technology, its performance still significantly degrades when facing non-neutrally-phonated (e.g., shouted and whispered) speech. To address this issue, in this paper, we propose a new speaker embedding compensation method based on a minimum mean square error (MMSE) estimator. This method models the joint distribution of the vocal effort transfer vector and non-neutrally-phonated embedding spaces and operates in a principal component analysis domain to cope with non-neutrally-phonated speech data scarcity. Experiments are carried out using a cutting-edge speaker verification system integrating a powerful self-supervised pre-trained model for speech representation. In comparison with a state-of-the-art embedding compensation method, the proposed MMSE estimator yields superior and competitive equal error rate results when tackling shouted and whispered speech, respectively.

Keywords

Cite

@article{arxiv.2305.02147,
  title  = {Improved Vocal Effort Transfer Vector Estimation for Vocal Effort-Robust Speaker Verification},
  author = {Iván López-Espejo and Santi Prieto and Alfonso Ortega and Eduardo Lleida},
  journal= {arXiv preprint arXiv:2305.02147},
  year   = {2023}
}
R2 v1 2026-06-28T10:24:36.403Z