In defence of metric learning for speaker recognition

Joon Son Chung, Jaesung Huh, Seongkyu Mun, Minjae Lee, Hee Soo Heo +5 more
3/26/2020
eess.AScs.SD

Official code: clovaai/voxceleb_trainer (1,176 stars, MIT, last commit 2026-04-22).

Abstract

The objective of this paper is 'open-set' speaker recognition of unseen speakers, where ideal embeddings should be able to condense information into a compact utterance-level representation that has small intra-speaker and large inter-speaker distance. A popular belief in speaker recognition is that networks trained with classification objectives outperform metric learning methods. In this paper, we present an extensive evaluation of most popular loss functions for speaker recognition on the VoxCeleb dataset. We demonstrate that the vanilla triplet loss shows competitive performance compared to classification-based losses, and those trained with our proposed metric learning objective outperform state-of-the-art methods.

View on arXivView PDF

Code Implementations(1)

clovaai/voxceleb_trainerOfficial100%
MIT

In defence of metric learning for speaker recognition

1,176290PythonMar 26, 20206 months agoMIT
metric-learningspeaker-recognitionspeaker-verificationvoxceleb

Similar Papers

Speech2Phone: A Novel and Efficient Method for Training Speaker Recognition Models

82% match1 repo92020

Utterance-level Aggregation For Speaker Recognition In The Wild

80% match1 repo3722019

Improving the Gap in Visual Speech Recognition Between Normal and Silent Speech Based on Metric Learning

79% match2023

Disentangling Speaker Traits for Deepfake Source Verification via Chebyshev Polynomial and Riemannian Metric Learning

79% match1 repo22026

Metric Learning Encoding Models: A Multivariate Framework for Interpreting Neural Representations

79% match1 repo32024

Evaluation of Speech Representations for MOS prediction

79% match1 repo102023

Cite this paper

@article{chung2020defence,
  title  = {In defence of metric learning for speaker recognition},
  author = {Joon Son Chung and Jaesung Huh and Seongkyu Mun and Minjae Lee and Hee Soo Heo and Soyeon Choe and Chiheon Ham and Sunghwan Jung and Bong-Jin Lee and Icksang Han},
  year   = {2020},
  eprint = {2003.11982},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2003.11982}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2003.11982.svg)](https://codeofpaper.com/paper/2003.11982)

Discussion