Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Enhancing Multi-Corpus Training in SSL-Based Anti-Spoofing Models: Domain-Invariant Feature Extraction

Anh-Tuan Dao, Driss Matrouf, Mickael Rouvier, Nicholas Evans

Abstract

The performance of speech spoofing detection often varies across different training and evaluation corpora. Leveraging multiple corpora typically enhances robustness and performance in fields like speaker recognition and speech recognition. However, our spoofing detection experiments show that multi-corpus training does not consistently improve performance and may even degrade it. We hypothesize that dataset-specific biases impair generalization, leading to performance instability. To address this, we propose an Invariant Domain Feature Extraction (IDFE) framework, employing multi-task learning and a gradient reversal layer to minimize corpus-specific information in learned embeddings. The IDFE framework reduces the average equal error rate by 20% compared to the baseline, assessed across four varied datasets.

Enhancing Multi-Corpus Training in SSL-Based Anti-Spoofing Models: Domain-Invariant Feature Extraction

Abstract

The performance of speech spoofing detection often varies across different training and evaluation corpora. Leveraging multiple corpora typically enhances robustness and performance in fields like speaker recognition and speech recognition. However, our spoofing detection experiments show that multi-corpus training does not consistently improve performance and may even degrade it. We hypothesize that dataset-specific biases impair generalization, leading to performance instability. To address this, we propose an Invariant Domain Feature Extraction (IDFE) framework, employing multi-task learning and a gradient reversal layer to minimize corpus-specific information in learned embeddings. The IDFE framework reduces the average equal error rate by 20% compared to the baseline, assessed across four varied datasets.
Paper Structure (18 sections, 4 equations, 2 figures, 2 tables)

This paper contains 18 sections, 4 equations, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. SSL-based Spoofing Detection
  3. SSL Feature Extractors
  4. Back-end Classifiers
  5. Invariant Domain Feature Extraction
  6. Architecture
  7. Domain Adversarial Training
  8. Backpropagation and Parameter Updates
  9. Experimental Setup
  10. Datasets and Metrics
  11. Data Augmentation
  12. Implementation Details
  13. Results
  14. Dataset Bias Analysis
  15. Multi-Corpus Training Performance
  16. ...and 3 more sections

Figures (2)

  • Figure 1: Our model architecture with dual classifiers and GRL.
  • Figure 2: t-SNE visualization of learned embeddings from the MHFA and MHFA-IDFE models for the training case 4. The parameter $\alpha$ controls the strength of domain invariance, as defined in Equation \ref{['eq1']}.