arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.03339eess.AS
收藏

用于语音增强的增强自监督嵌入

Boosting Self-Supervised Embeddings for Speech Enhancement

Kuo-Hsuan Hung, Szu-wei Fu, Huan-Hsin Tseng, Hsin-Tien Chiang, Yu Tsao, Chii-Wann Lin

摘要:

语音的自监督学习(SSL)表示在几个下游任务上已经达到了最先进的(SOTA)性能。然而,在语音增强(SE)任务中仍然存在改进的空间。在这项研究中,我们使用了跨域功能来解决SSL嵌入可能缺乏细粒度信息来重新生成语音信号的问题。通过整合SSL表示和频谱图,可以显着提高结果。我们进一步研究了SSL表示的噪声鲁棒性之间的关系,通过清洁噪声距离(CN距离)和层的重要性SE。因此,我们发现具有较低噪声鲁棒性的SSL表示更重要。此外,我们在VCTK-DEMAND数据集上的实验表明,使用SE模型微调SSL表示可以在PESQ,CSIG和COVL中优于SOTA基于SSL的SE方法,而无需调用复杂的网络架构。在后来的实验中,观察到SSL嵌入中的CN距离在微调后增加。这些结果验证了我们的预期,并可能有助于设计SE相关的SSL培训在未来。

英文摘要:

Self-supervised learning (SSL) representation for speech has achieved state-of-the-art (SOTA) performance on several downstream tasks. However, there remains room for improvement in speech enhancement (SE) tasks. In this study, we used a cross-domain feature to solve the problem that SSL embeddings may lack fine-grained information to regenerate speech signals. By integrating the SSL representation and spectrogram, the result can be significantly boosted. We further study the relationship between the noise robustness of SSL representation via clean-noisy distance (CN distance) and the layer importance for SE. Consequently, we found that SSL representations with lower noise robustness are more important. Furthermore, our experiments on the VCTK-DEMAND dataset demonstrated that fine-tuning an SSL representation with an SE model can outperform the SOTA SSL-based SE methods in PESQ, CSIG and COVL without invoking complicated network architectures. In later experiments, the CN distance in SSL embeddings was observed to increase after fine-tuning. These results verify our expectations and may help design SE-related SSL training in the future.

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。

↑