Emphasized Non-Target Speaker Knowledge in Knowledge Distillation for Automatic Speaker Verification

Duc Tuan Truong, Ruijie Tao, Jia Qi Yip, Kong Aik Lee, Eng Siong Chng

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

Abstract

Knowledge distillation (KD) is used to enhance automatic speaker verification performance by ensuring consistency between large teacher networks and lightweight student networks at the embedding level or label level. However, the conventional label-level KD overlooks the significant knowledge from non-target speakers, particularly their classification probabilities, which can be crucial for automatic speaker verification. In this paper, we first demonstrate that leveraging a larger number of training non-target speakers improves the performance of automatic speaker verification models. Inspired by this finding about the importance of non-target speakers' knowledge, we modified the conventional label-level KD by disentangling and emphasizing the classification probabilities of non-target speakers during knowledge distillation. The proposed method is applied to three different student model architectures and achieves an average of 13.67% improvement in EER on the VoxCeleb dataset compared to embedding-level and conventional label-level KD methods.

Original languageEnglish
Title of host publication2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages10336-10340
Number of pages5
ISBN (Electronic)9798350344851
DOIs
Publication statusPublished - 14 Apr 2024
Event49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Seoul, Korea, Republic of
Duration: 14 Apr 202419 Apr 2024

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149

Conference

Conference49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024
Country/TerritoryKorea, Republic of
CitySeoul
Period14/04/2419/04/24

Keywords

  • automatic speaker verification
  • knowledge distillation
  • label-level knowledge distillation

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Emphasized Non-Target Speaker Knowledge in Knowledge Distillation for Automatic Speaker Verification'. Together they form a unique fingerprint.

Cite this