Unsupervised Adaptive Speaker Recognition by Coupling-Regularized Optimal Transport

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F24%3APU156211" target="_blank" >RIV/00216305:26230/24:PU156211 - isvavai.cz</a>

Výsledek na webu

<a href="https://xplorestaging.ieee.org/document/10596689?denied" target="_blank" >https://xplorestaging.ieee.org/document/10596689?denied</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TASLP.2024.3426934" target="_blank" >10.1109/TASLP.2024.3426934</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Unsupervised Adaptive Speaker Recognition by Coupling-Regularized Optimal Transport

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Unsupervised Adaptive Speaker Recognition by Coupling-Regularized Optimal Transport

Popis výsledku anglicky

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.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10300 - Physical sciences

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING

ISSN

2329-9290

e-ISSN

2329-9304

Svazek periodika

32

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

15

Strana od-do

3603-3617

Kód UT WoS článku

001283673700022

EID výsledku v databázi Scopus

2-s2.0-85198359234