arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.08400eess.AScs.SD
收藏

语音分离网络中分离层的再思考

Rethinking the Separation Layers in Speech Separation Networks

Columbia University(哥伦比亚大学);Shanghai Jiao Tong University(上海交通大学);Microsoft Corporation(微软公司)

Yi Luo, Zhuo Chen, Cong Han, Chenda Li, Tianyan Zhou, Nima Mesgarani

摘要:

现有语音分离网络中的模块可以分为单输入多输出(SIMO)模块和单输入单输出(SISO)模块。SIMO模块生成的输出比输入多,SISO模块保持输入和输出的数量相同。虽然大多数分离模型只包含SIMO结构,但也表明某些两级分离系统与后增强SISO模块集成可以提高分离质量。为什么通过整合SISO模块可以实现性能提升?SIMO模块是否总是必需的?在本文中,我们通过设计SIMO和SISO模块中具有不同配置的模型来实证研究这些问题。我们发现,与标准的SIMO设计相比,具有相同的模型尺寸的混合SIMO-SISO设计能够提高分离性能,特别是在低重叠条件下。我们进一步验证了SIMO模块的必要性,并表明SISO模型仍然能够在不牺牲性能的情况下执行分离。这些观察使我们能够重新思考模型设计范式,并就如何执行分离提出不同的观点。

英文摘要:

Modules in all existing speech separation networks can be categorized into single-input-multi-output (SIMO) modules and single-input-single-output (SISO) modules. SIMO modules generate more outputs than input, and SISO modules keep the numbers of input and output the same. While the majority of separation models only contain SIMO architectures, it has also been shown that certain two-stage separation systems integrated with a post-enhancement SISO module can improve the separation quality. Why performance improvements can be achieved by incorporating the SISO modules? Are SIMO modules always necessary? In this paper, we empirically examine those questions by designing models with varying configurations in the SIMO and SISO modules. We show that comparing with the standard SIMO-only design, a mixed SIMO-SISO design with a same model size is able to improve the separation performance especially under low-overlap conditions. We further validate the necessity of SIMO modules and show that SISO-only models are still able to perform separation without sacrificing the performance. The observations allow us to rethink the model design paradigm and present different views on how the separation is performed.

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。

↑