@inproceedings{1e9e1d5f26134382be818008f0567031,
title = "Shouted Speech Compensation for Speaker Verification Robust to Vocal Effort Conditions",
abstract = "The performance of speaker verification systems degrades when vocal effort conditions between enrollment and test (e.g., shouted vs. normal speech) are different. This is a potential situation in non-cooperative speaker verification tasks. In this paper, we present a study on different methods for linear compensation of embeddings making use of Gaussian mixture models to cluster shouted and normal speech domains. These compensation techniques are borrowed from the area of robustness for automatic speech recognition and, in this work, we apply them to compensate the mismatch between shouted and normal conditions in speaker verification. Before compensation, shouted condition is automatically detected by means of logistic regression. The process is computationally light and it is performed in the back-end of an x-vector system. Experimental results show that applying the proposed approach in the presence of vocal effort mismatch yields up to 13.8% equal error rate relative improvement with respect to a system that applies neither shouted speech detection nor compensation.",
keywords = "Domain compensation, Shouted speech, Speaker verification, Vocal effort mismatch",
author = "Santiago Prieto-Calero and Alfonso Ortega and Espejo, {Iv{\'a}n L{\'o}pez} and Eduardo Lleida",
year = "2020",
doi = "10.21437/Interspeech.2020-1402",
language = "English",
series = "Proceedings of the International Conference on Spoken Language Processing",
publisher = "International Speech Communication Association",
pages = "1511--1515",
booktitle = "Interspeech 2020",
note = "Interspeech 2020 ; Conference date: 25-10-2020 Through 29-10-2020",
}