arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.00264cs.SDeess.AS
收藏

基于距离的近场到远场说话人确认权值传递

Distance-based Weight Transfer from Near-field to Far-field Speaker Verification

Northwestern Polytechnical University(西北工业大学);Tencent Corporation(腾讯公司)

Li Zhang, Qing Wang, Hongji Wang, Yue Li, Wei Rao, Yannan Wang, Lei Xie

摘要:

标记远场语音的稀缺性是训练高性能远场说话人确认系统的一个制约因素。对大规模近场语音预训练的模型进行微调,大大优于从头开始的训练。然而,微调方法受到两个限制-灾难性遗忘和过拟合。在本文中,我们提出了一种权重转移正则化(WTR)损失来约束具有大规模近场语音的预训练模型与通过少量远场语音进行微调的模型之间的权重距离。在WTR损失的情况下,微调过程利用了先前从大规模近场语音获得的辨别能力,而没有灾难性遗忘。同时,我们利用PAC-Bayes推广理论分析了具有WTR损失的微调模型的推广界。分析结果表明,WTR项的引入使得模型的泛化上界更紧。此外,我们探讨了三种范数距离的权重转移,这是L1-范数距离,L2-范数距离和最大范数距离。最后,我们评估了VoxCeleb(预训练数据集)和FFSVC(微调数据集)数据集上WTR损失的有效性。

英文摘要:

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 upper bound. Moreover, we explore three kinds of norm distance for weight transfer, which are L1-norm distance, L2-norm distance and Max-norm distance. Finally, we evaluate the effectiveness of the WTR loss on VoxCeleb (pre-trained dataset) and FFSVC (fine-tuned dataset) datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑