Speaker Verification Using End-to-end Adversarial Language Adaptation

Abstract

In this paper we investigate the use of adversarial domain adaptation for addressing the problem of language mismatch between speaker recognition corpora. In the context of speaker verification, adversarial domain adaptation methods aim at minimizing certain divergences between the distribution that the utterance-level features follow (i.e. speaker embeddings) when drawn from source and target domains (i.e. languages), while preserving their capacity in recognizing speakers. Neural architectures for extracting utterance-level representations enable us to apply adversarial adaptation methods in an end-to-end fashion and train the network jointly with the standard cross-entropy loss. We examine several configurations, such as the use of (pseudo-)labels on the target domain as well as domain labels in the feature extractor, and we demonstrate the effectiveness of our method on the challenging NIST SRE16 and SRE18 benchmarks.

Stats

• citations30
• S2 citations—
• github stars0
• HF likes0
• heat score11.19
• arxiv keyrohdin2018speaker

Related papers

• Adapting End-to-end Neural Speaker Verification To New Languages And Recording Conditions With Adversarial Training (2018)9.59
• DEAAN: Disentangled Embedding And Adversarial Adaptation Network For Robust Speaker Representation Learning (2020)9.59
• Cross-lingual Text-independent Speaker Verification Using Unsupervised Adversarial Discriminative Domain Adaptation (2019)11.85
• Source -free Domain Adaptation For Speaker Verification In Data-scarce Languages And Noisy Channels (2024)0.00
• Vae-based Domain Adaptation For Speaker Verification (2019)7.50
• Multi-domain Adaptation By Self-supervised Learning For Speaker Verification (2023)0.00
• Generative Adversarial Speaker Embedding Networks For Domain Robust End-to-end Speaker Verification (2018)0.00
• Unsupervised Domain Adaptation By Adversarial Learning For Robust Speech Recognition (2018)0.00