Publication Details

Challenging margin-based speaker embedding extractors by using the variational information bottleneck

STAFYLAKIS, T.; SILNOVA, A.; ROHDIN, J.; PLCHOT, O.; BURGET, L. Challenging margin-based speaker embedding extractors by using the variational information bottleneck. In Proceedings of Interspeech 2024. Proceedings of Interspeech. Kos: International Speech Communication Association, 2024. p. 3220-3224. ISSN: 1990-9772.
Czech title
Extraktory embeddingů řečníků pro náročné okrajové podmínky s variačním informačním bottleneckem
Type
conference paper
Language
English
Authors
URL
Keywords

speaker recognition, variational information bottleneck

Abstract

Speaker embedding extractors are typically trained using a classification loss
over the training speakers. During the last few years, the standard
softmax/cross-entropy loss has been replaced by the margin-based losses, yielding
significant im- provements in speaker recognition accuracy. Motivated by the fact
that the margin merely reduces the logit of the target speaker during training,
we consider a probabilistic framework that has a similar effect. The variational
information bottle- neck provides a principled mechanism for making deterministic
nodes stochastic, resulting in an implicit reduction of the pos- terior of the
target speaker. We experiment with a wide range of speaker recognition benchmarks
and scoring methods and re- port competitive results to those obtained with the
state-of-the- art Additive Angular Margin loss.

Published
2024
Pages
3220–3224
Journal
Proceedings of Interspeech, vol. 2024, no. 9, ISSN 1990-9772
Proceedings
Proceedings of Interspeech 2024
Conference
Interspeech Conference, Kos, GR
Publisher
International Speech Communication Association
Place
Kos
DOI
EID Scopus
BibTeX
@inproceedings{BUT193738,
  author="Themos {Stafylakis} and Anna {Silnova} and Johan Andréas {Rohdin} and Oldřich {Plchot} and Lukáš {Burget}",
  title="Challenging margin-based speaker embedding extractors by using the variational information bottleneck",
  booktitle="Proceedings of Interspeech 2024",
  year="2024",
  journal="Proceedings of Interspeech",
  volume="2024",
  number="9",
  pages="3220--3224",
  publisher="International Speech Communication Association",
  address="Kos",
  doi="10.21437/Interspeech.2024-2058",
  issn="1990-9772",
  url="https://www.isca-archive.org/interspeech_2024/stafylakis24_interspeech.pdf"
}
Files
Back to top