Cross-domain Adaptation with Discrepancy Minimization for Text-independent Forensic Speaker Verification

by   Zhenyu Wang, et al.

Forensic audio analysis for speaker verification offers unique challenges due to location/scenario uncertainty and diversity mismatch between reference and naturalistic field recordings. The lack of real naturalistic forensic audio corpora with ground-truth speaker identity represents a major challenge in this field. It is also difficult to directly employ small-scale domain-specific data to train complex neural network architectures due to domain mismatch and loss in performance. Alternatively, cross-domain speaker verification for multiple acoustic environments is a challenging task which could advance research in audio forensics. In this study, we introduce a CRSS-Forensics audio dataset collected in multiple acoustic environments. We pre-train a CNN-based network using the VoxCeleb data, followed by an approach which fine-tunes part of the high-level network layers with clean speech from CRSS-Forensics. Based on this fine-tuned model, we align domain-specific distributions in the embedding space with the discrepancy loss and maximum mean discrepancy (MMD). This maintains effective performance on the clean set, while simultaneously generalizes the model to other acoustic domains. From the results, we demonstrate that diverse acoustic environments affect the speaker verification performance, and that our proposed approach of cross-domain adaptation can significantly improve the results in this scenario.


Impact of Naturalistic Field Acoustic Environments on Forensic Text-independent Speaker Verification System

Audio analysis for forensic speaker verification offers unique challenge...

Squeezing value of cross-domain labels: a decoupled scoring approach for speaker verification

Domain mismatch often occurs in real applications and causes serious per...

DEAAN: Disentangled Embedding and Adversarial Adaptation Network for Robust Speaker Representation Learning

Despite speaker verification has achieved significant performance improv...

The HCCL System for the NIST SRE21

This paper describes the systems developed by the HCCL team for the NIST...

CNN-based Discriminative Training for Domain Compensation in Acoustic Event Detection with Frame-wise Classifier

Domain mismatch is a noteworthy issue in acoustic event detection tasks,...

Red Carpet to Fight Club: Partially-supervised Domain Transfer for Face Recognition in Violent Videos

In many real-world problems, there is typically a large discrepancy betw...

Robust Acoustic Domain Identification with its Application to Speaker Diarization

With the rise in multimedia content over the years, more variety is obse...