在使用大型预训练自监督学习模型进行说话人验证中的单步知识蒸馏与微调
One-Step Knowledge Distillation and Fine-Tuning in Using Large Pre-Trained Self-Supervised Learning Models for Speaker Verification
AI总结：
针对说话人验证中大型SSL模型计算成本高的问题，提出OS-KDFT，在知识蒸馏中同步面向SV微调学生模型，实现显著压缩、加速与低EER。
摘要：
语音自监督学习（SSL）模型的应用已在说话人验证（SV）中取得显著性能。然而，使用这些模型存在计算成本障碍，导致开发和部署困难。若干研究仅通过知识蒸馏（KD）压缩SSL模型，而未考虑目标任务。因此，这些方法无法提取为SV定制的特征。本文提出单步知识蒸馏与微调（OS-KDFT），将KD与微调（FT）相结合。我们在KD训练期间针对SV优化学生模型，以避免蒸馏不适合SV的信息。OS-KDFT可将基于Wav2Vec 2.0的ECAPA-TDNN规模缩小约76.2%，并将SSL模型的推理时间减少79%，同时实现0.98%的EER。所提出的OS-KDFT在VoxCeleb1和VoxCeleb2数据集以及W2V2和HuBERT SSL模型上得到验证。实验可在我们的GitHub上获取。
英文摘要：
The application of speech self-supervised learning (SSL) models has achieved remarkable performance in speaker verification (SV). However, there is a computational cost hurdle in employing them, which makes development and deployment difficult. Several studies have simply compressed SSL models through knowledge distillation (KD) without considering the target task. Consequently, these methods could not extract SV-tailored features. This paper suggests One-Step Knowledge Distillation and Fine-Tuning (OS-KDFT), which incorporates KD and fine-tuning (FT). We optimize a student model for SV during KD training to avert the distillation of inappropriate information for the SV. OS-KDFT could downsize Wav2Vec 2.0 based ECAPA-TDNN size by approximately 76.2%, and reduce the SSL model's inference time by 79% while presenting an EER of 0.98%. The proposed OS-KDFT is validated across VoxCeleb1 and VoxCeleb2 datasets and W2V2 and HuBERT SSL models. Experiments are available on our GitHub.
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。
