利用ASR预训练Conformer通过迁移学习和知识蒸馏进行说话人验证
Leveraging ASR Pretrained Conformers for Speaker Verification through Transfer Learning and Knowledge Distillation
AI总结：
本文利用ASR预训练Conformer，通过迁移学习、知识蒸馏和轻量级适配器三种策略，在VoxCeleb上实现低至0.43%的EER，有效迁移ASR能力至说话人验证。
摘要：
本文探讨了将ASR预训练的Conformer用于说话人验证，利用其在语音信号建模方面的优势。我们提出了三种策略：（1）迁移学习初始化说话人嵌入网络，提高泛化能力并减少过拟合。（2）知识蒸馏训练更灵活的说话人验证模型，将帧级ASR损失作为辅助任务纳入其中。（3）轻量级说话人适配器，在不改变原始ASR Conformer的情况下实现高效特征转换，允许ASR和说话人验证并行进行。在VoxCeleb上的实验显示了显著改进：迁移学习实现了0.48%的等错误率（EER），知识蒸馏实现了0.43%的EER，而说话人适配器方法仅向130.94M参数的模型添加了4.92M参数，达到了0.57%的EER。总体而言，我们的方法有效地将ASR能力迁移到说话人验证任务中。
英文摘要：
This paper explores the use of ASR-pretrained Conformers for speaker verification, leveraging their strengths in modeling speech signals. We introduce three strategies: (1) Transfer learning to initialize the speaker embedding network, improving generalization and reducing overfitting. (2) Knowledge distillation to train a more flexible speaker verification model, incorporating frame-level ASR loss as an auxiliary task. (3) A lightweight speaker adaptor for efficient feature conversion without altering the original ASR Conformer, allowing parallel ASR and speaker verification. Experiments on VoxCeleb show significant improvements: transfer learning yields a 0.48% EER, knowledge distillation results in a 0.43% EER, and the speaker adaptor approach, with just an added 4.92M parameters to a 130.94M-parameter model, achieves a 0.57% EER. Overall, our methods effectively transfer ASR capabilities to speaker verification tasks.
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。
