arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.09320cs.SDeess.AS
收藏

从近场到远场说话人确认的多级迁移学习

Multi-Level Transfer Learning from Near-Field to Far-Field Speaker Verification

Northwestern Polytechnical University(西北工业大学);National University of Singapore(新加坡国立大学)

Li Zhang, Qing Wang, Kong Aik Lee, Lei Xie, Haizhou Li

摘要:

在远场说话人确认中,当注册条件和测试语音条件不匹配时,说话人嵌入的性能容易下降。为了解决这个问题,我们提出了教师-学生框架下的特征级和实例级迁移学习来学习一个域不变的嵌入空间。对于特征级的知识传递,我们提出了教师模型到学生模型的对比损失传递方法,不仅可以缩小类内距离,而且可以扩大类间距离。此外,我们提出了实例级的成对距离转移方法,以迫使学生模型保持成对实例与教师模型的优化嵌入空间的距离。在FFSVC 2020评估集上,与Task 2的部分评估试验的融合系统结果相比,我们的完整评估试验的EER相对降低了13.9%。在任务1上,与获胜者在部分评估试验上的DenseNet结果相比,我们在完全评估试验上的minDCF相对减少了6.3%。在任务3上,我们所提出的方法在完整评估试验上的EER和minDCF非常接近于融合系统在部分评估试验上的结果。我们的结果也优于其他竞争领域自适应方法。

英文摘要:

In far-field speaker verification, the performance of speaker embeddings is susceptible to degradation when there is a mismatch between the conditions of enrollment and test speech. To solve this problem, we propose the feature-level and instance-level transfer learning in the teacher-student framework to learn a domain-invariant embedding space. For the feature-level knowledge transfer, we develop the contrastive loss to transfer knowledge from teacher model to student model, which can not only decrease the intra-class distance, but also enlarge the inter-class distance. Moreover, we propose the instance-level pairwise distance transfer method to force the student model to preserve pairwise instances distance from the well optimized embedding space of the teacher model. On FFSVC 2020 evaluation set, our EER on Full-eval trials is relatively reduced by 13.9% compared with the fusion system result on Partial-eval trials of Task2. On Task1, compared with the winner's DenseNet result on Partial-eval trials, our minDCF on Full-eval trials is relatively reduced by 6.3%. On Task3, the EER and minDCF of our proposed method on Full-eval trials are very close to the result of the fusion system on Partial-eval trials. Our results also outperform other competitive domain adaptation methods.

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。

↑