Squeezing Value Of Cross-domain Labels: A Decoupled Scoring Approach For Speaker Verification

Abstract

Domain mismatch often occurs in real applications and causes serious performance reduction on speaker verification systems. The common wisdom is to collect cross-domain data and train a multi-domain PLDA model, with the hope to learn a domain-independent speaker subspace. In this paper, we firstly present an empirical study to show that simply adding cross-domain data does not help performance in conditions with enrollment-test mismatch. Careful analysis shows that this striking result is caused by the incoherent statistics between the enrollment and test conditions. Based on this analysis, we present a decoupled scoring approach that can maximally squeeze the value of cross-domain labels and obtain optimal verification scores when the enrollment and test are mismatched. When the statistics are coherent, the new formulation falls back to the conventional PLDA. Experimental results on cross-channel test show that the proposed approach is highly effective and is a principle solution to d

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyli2020squeezing

Related papers

• Analyzing Speaker Verification Embedding Extractors And Back-ends Under Language And Channel Mismatch (2022)0.00
• Domain Adaptation Based Speaker Recognition On Short Utterances (2016)0.00
• Cross-lingual Text-independent Speaker Verification Using Unsupervised Adversarial Discriminative Domain Adaptation (2019)11.85
• Adversarial Training For Multi-domain Speaker Recognition (2020)6.77
• Multiobjective Optimization Training Of PLDA For Speaker Verification (2018)2.26
• Multi-domain Adaptation By Self-supervised Learning For Speaker Verification (2023)0.00
• Channel Adaptation For Speaker Verification Using Optimal Transport With Pseudo Label (2024)0.00
• A Generalized Framework For Domain Adaptation Of PLDA In Speaker Recognition (2020)7.50