Distance-based Weight Transfer From Near-field To Far-field Speaker Verification

Abstract

The scarcity of labeled far-field speech is a constraint for training superior far-field speaker verification systems. Fine-tuning the model pre-trained on large-scale near-field speech substantially outperforms training from scratch. However, the fine-tuning method suffers from two limitations--catastrophic forgetting and overfitting. In this paper, we propose a weight transfer regularization(WTR) loss to constrain the distance of the weights between the pre-trained model with large-scale near-field speech and the fine-tuned model through a small number of far-field speech. With the WTR loss, the fine-tuning process takes advantage of the previously acquired discriminative ability from the large-scale near-field speech without catastrophic forgetting. Meanwhile, we use the PAC-Bayes generalization theory to analyze the generalization bound of the fine-tuned model with the WTR loss. The analysis result indicates that the WTR term makes the fine-tuned model have a tighter generalization

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2023distance

Related papers

• Multi-level Transfer Learning From Near-field To Far-field Speaker Verification (2021)0.00
• Task-specific Optimization Of Virtual Channel Linear Prediction-based Speech Dereverberation Front-end For Far-field Speaker Verification (2021)2.26
• Single Channel Far Field Feature Enhancement For Speaker Verification In The Wild (2020)0.00
• Developing Far-field Speaker System Via Teacher-student Learning (2018)10.85
• Leveraging ASR Pretrained Conformers For Speaker Verification Through Transfer Learning And Knowledge Distillation (2023)10.74
• Speech-ft: Merging Pre-trained And Fine-tuned Speech Representation Models For Cross-task Generalization (2026)2.94
• Parameterized Channel Normalization For Far-field Deep Speaker Verification (2021)3.58
• Enhancing Speaker Verification With W2v-bert 2.0 And Knowledge Distillation Guided Structured Pruning (2025)3.33