Cargando…

Few-shot short utterance speaker verification using meta-learning

Short utterance speaker verification (SV) in the actual application is the task of accepting or rejecting the identity claim of a speaker based on a few enrollment utterances. Traditional methods have used deep neural networks to extract speaker representations for verification. Recently, several me...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Weijie, Zhao, Hong, Yang, Yikun, Chang, YouKang, You, Haojie
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10280689/
https://www.ncbi.nlm.nih.gov/pubmed/37346533
http://dx.doi.org/10.7717/peerj-cs.1276
_version_ 1785060853171617792
author Wang, Weijie
Zhao, Hong
Yang, Yikun
Chang, YouKang
You, Haojie
author_facet Wang, Weijie
Zhao, Hong
Yang, Yikun
Chang, YouKang
You, Haojie
author_sort Wang, Weijie
collection PubMed
description Short utterance speaker verification (SV) in the actual application is the task of accepting or rejecting the identity claim of a speaker based on a few enrollment utterances. Traditional methods have used deep neural networks to extract speaker representations for verification. Recently, several meta-learning approaches have learned a deep distance metric to distinguish speakers within meta-tasks. Among them, a prototypical network learns a metric space that may be used to compute the distance to the prototype center of speakers, in order to classify speaker identity. We use emphasized channel attention, propagation and aggregation in TDNN (ECAPA-TDNN) to implement the necessary function for the prototypical network, which is a nonlinear mapping from the input space to the metric space for either few-shot SV task. In addition, optimizing only for speakers in given meta-tasks cannot be sufficient to learn distinctive speaker features. Thus, we used an episodic training strategy, in which the classes of the support and query sets correspond to the classes of the entire training set, further improving the model performance. The proposed model outperforms comparison models on the VoxCeleb1 dataset and has a wide range of practical applications.
format Online
Article
Text
id pubmed-10280689
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-102806892023-06-21 Few-shot short utterance speaker verification using meta-learning Wang, Weijie Zhao, Hong Yang, Yikun Chang, YouKang You, Haojie PeerJ Comput Sci Artificial Intelligence Short utterance speaker verification (SV) in the actual application is the task of accepting or rejecting the identity claim of a speaker based on a few enrollment utterances. Traditional methods have used deep neural networks to extract speaker representations for verification. Recently, several meta-learning approaches have learned a deep distance metric to distinguish speakers within meta-tasks. Among them, a prototypical network learns a metric space that may be used to compute the distance to the prototype center of speakers, in order to classify speaker identity. We use emphasized channel attention, propagation and aggregation in TDNN (ECAPA-TDNN) to implement the necessary function for the prototypical network, which is a nonlinear mapping from the input space to the metric space for either few-shot SV task. In addition, optimizing only for speakers in given meta-tasks cannot be sufficient to learn distinctive speaker features. Thus, we used an episodic training strategy, in which the classes of the support and query sets correspond to the classes of the entire training set, further improving the model performance. The proposed model outperforms comparison models on the VoxCeleb1 dataset and has a wide range of practical applications. PeerJ Inc. 2023-04-21 /pmc/articles/PMC10280689/ /pubmed/37346533 http://dx.doi.org/10.7717/peerj-cs.1276 Text en ©2023 Wang et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited.
spellingShingle Artificial Intelligence
Wang, Weijie
Zhao, Hong
Yang, Yikun
Chang, YouKang
You, Haojie
Few-shot short utterance speaker verification using meta-learning
title Few-shot short utterance speaker verification using meta-learning
title_full Few-shot short utterance speaker verification using meta-learning
title_fullStr Few-shot short utterance speaker verification using meta-learning
title_full_unstemmed Few-shot short utterance speaker verification using meta-learning
title_short Few-shot short utterance speaker verification using meta-learning
title_sort few-shot short utterance speaker verification using meta-learning
topic Artificial Intelligence
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10280689/
https://www.ncbi.nlm.nih.gov/pubmed/37346533
http://dx.doi.org/10.7717/peerj-cs.1276
work_keys_str_mv AT wangweijie fewshotshortutterancespeakerverificationusingmetalearning
AT zhaohong fewshotshortutterancespeakerverificationusingmetalearning
AT yangyikun fewshotshortutterancespeakerverificationusingmetalearning
AT changyoukang fewshotshortutterancespeakerverificationusingmetalearning
AT youhaojie fewshotshortutterancespeakerverificationusingmetalearning