Mutual Information Enhanced Training for Speaker Embedding

Youzhi Tu, Man Wai Mak

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

1 Citation (Scopus)

Abstract

Mutual information (MI) is useful in unsupervised and selfsupervised learning. Maximizing the MI between the low-level features and the learned embeddings can preserve meaningful information in the embeddings, which can contribute to performance gains. This strategy is called deep InfoMax (DIM) in representation learning. In this paper, we follow the DIM framework so that the speaker embeddings can capture more information from the frame-level features. However, a straightforward implementation of DIM may pose a dimensionality imbalance problem because the dimensionality of the frame-level features is much larger than that of the speaker embeddings. This problem can lead to unreliable MI estimation and can even cause detrimental effects on speaker verification. To overcome this problem, we propose to squeeze the frame-level features before MI estimation through some global pooling methods. We call the proposed method squeeze-DIM. Although the squeeze operation inevitably introduces some information loss, we empirically show that the squeeze-DIM can achieve performance gains on both Voxceleb1 and VOiCES-19 tasks. This suggests that the squeeze operation facilitates the MI estimation and maximization in a balanced dimensional space, which helps learn more informative speaker embeddings.

Original languageEnglish
Title of host publication22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
PublisherInternational Speech Communication Association
Pages661-665
Number of pages5
Volume1
ISBN (Electronic)9781713836902
DOIs
Publication statusPublished - Aug 2021
Event22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021 - Brno, Czech Republic
Duration: 30 Aug 20213 Sept 2021

Publication series

NameProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume1
ISSN (Print)2308-457X
ISSN (Electronic)1990-9772

Conference

Conference22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
Country/TerritoryCzech Republic
CityBrno
Period30/08/213/09/21

Keywords

  • Mutual information
  • Speaker embedding
  • Speaker verification
  • Variational lower bound

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modelling and Simulation

Fingerprint

Dive into the research topics of 'Mutual Information Enhanced Training for Speaker Embedding'. Together they form a unique fingerprint.

Cite this