Voice-quality Features for Deep Neural Network Based Speaker Verification Systems

Loading...
Thumbnail Image
Journal Title
Journal ISSN
Volume Title
Conference article in proceedings
Date
2021-08-27
Major/Subject
Mcode
Degree programme
Language
en
Pages
5
176-180
Series
29th European Signal Processing Conference, EUSIPCO 2021 - Proceedings, European Signal Processing Conference
Abstract
Jitter and shimmer are voice-quality features which have been successfully used to detect voice pathologies and classify different speaking styles. In this paper, we investigate the usefulness of such voice-quality features in neural-network based speaker verification systems. To combine these two sets of features, the cosine distance scores estimated from the two sets are linearly weighted to obtain a single, fused score. The fused score is used to accept/reject a given speaker. The experimental results carried out on Voxceleb-1 dataset demonstrate that the fusion of the cosine distance scores extracted from the mel-spectrogram and voice quality features provide a 15% relative improvement in Equal Error Rate (EER) compared to the baseline system which is based only on mel-spectrogram features.
Description
Keywords
jitter, mel-spectrogram, fusion, shimmer, speech recognition
Other note
Citation
Zewoudie, A, Koivisto, L & Bäckström, T 2021, Voice-quality Features for Deep Neural Network Based Speaker Verification Systems . in 29th European Signal Processing Conference, EUSIPCO 2021 - Proceedings . European Signal Processing Conference, IEEE, pp. 176-180, European Signal Processing Conference, Dublin, Ireland, 23/08/2021 . https://doi.org/10.23919/EUSIPCO54536.2021.9616242