arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.08342eess.AScs.SD
收藏

基于多粒度矢量量化的语音增强

Speech Enhancement with Multi-granularity Vector Quantization

University of Science and Technology of China (USTC)(中国科学技术大学(USTC))

Xiao-Ying Zhao, Qiu-Shi Zhu, Jie Zhang

摘要:

随着深度学习的进步,基于神经网络的语音增强(SE)在过去十年中得到了快速发展。同时,自监督预训练模型和矢量量化(VQ)在许多语音相关的任务上取得了优异的性能,而它们在SE上的探索较少。正如我们之前的工作所示,利用VQ模块离散化带噪语音表示有利于语音去噪,因此在这项工作中,我们研究了在不同层使用不同数量的码本的VQ的影响。不同的VQ模块确实能够提取多粒度语音特征。遵循注意机制,由预训练模型提取的上下文特征与由编码器提取的局部特征融合,使得全局和局部信息都被保留以重建增强的语音。在Valentini数据集上的实验结果表明,该模型可以提高SE性能,其中也揭示了选择预训练模型的影响。

英文摘要:

With advances in deep learning, neural network based speech enhancement (SE) has developed rapidly in the last decade. Meanwhile, the self-supervised pre-trained model and vector quantization (VQ) have achieved excellent performance on many speech-related tasks, while they are less explored on SE. As it was shown in our previous work that utilizing a VQ module to discretize noisy speech representations is beneficial for speech denoising, in this work we therefore study the impact of using VQ at different layers with different number of codebooks. Different VQ modules indeed enable to extract multiple-granularity speech features. Following an attention mechanism, the contextual features extracted by a pre-trained model are fused with the local features extracted by the encoder, such that both global and local information are preserved to reconstruct the enhanced speech. Experimental results on the Valentini dataset show that the proposed model can improve the SE performance, where the impact of choosing pre-trained models is also revealed.

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。

↑