Detail publikace

Unsupervised Adaptive Speaker Recognition by Coupling-Regularized Optimal Transport

ZHANG, R. WEI, J. LU, X. LU, W. JIN, D. ZHANG, L. XU, J.

Originální název

Unsupervised Adaptive Speaker Recognition by Coupling-Regularized Optimal Transport

Typ

článek v časopise ve Web of Science, Jimp

Jazyk

angličtina

Originální abstrakt

Cross-domain speaker recognition (SR) can be improved by unsupervised domain adaptation (UDA) algorithms. UDA algorithms often reduce domain mismatch at the cost of decreasing the discrimination of speaker features. In contrast, optimal transport (OT) has the potential to achieve domain alignment while preserving the speaker discrimination capability in UDA applications; however, naively applying OT to measure global probability distribution discrepancies between the source and target domains may induce negative transports where samples belonging to different speakers are coupled in transportation. These negative transports reduce the SR model's discriminative power, degrading the SR performance. This paper proposes a coupling-regularized optimal transport (CROT) algorithm for cross-domain SR to reduce the negative transport during UDA. In the proposed CROT, two consecutive processing modules regularize the coupling paths for the OT solution: a progressive inter-speaker constraint (PISC) module and a coupling-smoothed regularization (CSR) module. The PISC, designed as a pseudo-label memory bank with curriculum learning, is first applied to select valid samples to guarantee that coupling samples are from the same speaker. The CSR, designed to control the information entropy of the coupling paths further, reduces the effect of negative transport in UDA. To evaluate the effectiveness of the proposed algorithm, cross-domain SR experiments were conducted under different target domains, speaker encoders, corpora, and acoustic features. Experimental results showed that CROT achieved a 50% relative reduction in equal error rates compared to conventional OT-based UDAs, outperforming the state-of-the-art UDAs.

Klíčová slova

Speaker recognition; unsupervised domain adaptation; optimal transport; coupling regularization; Speaker recognition; unsupervised domain adaptation; optimal transport; coupling regularization

Autoři

ZHANG, R.; WEI, J.; LU, X.; LU, W.; JIN, D.; ZHANG, L.; XU, J.

Vydáno

31. 12. 2024

Nakladatel

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

Místo

PISCATAWAY

ISSN

2329-9290

Periodikum

IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING

Ročník

32

Číslo

1

Stát

Spojené státy americké

Strany od

3603

Strany do

3617

Strany počet

15

URL

https://xplorestaging.ieee.org/document/10596689?denied

BibTex

@article{BUT197616,
  author="Ruiteng {Zhang} and Jianguo {Wei} and Xugang {Lu} and Wenhuan {Lu} and Di {Jin} and Lin {Zhang} and Junhai {Xu}",
  title="Unsupervised Adaptive Speaker Recognition by Coupling-Regularized Optimal Transport",
  journal="IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING",
  year="2024",
  volume="32",
  number="1",
  pages="3603--3617",
  doi="10.1109/TASLP.2024.3426934",
  issn="2329-9290",
  url="https://xplorestaging.ieee.org/document/10596689?denied"
}