arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.07579eess.AS
收藏

Dual-Path Filter Network:说话人感知的语音分离建模

Dual-Path Filter Network: Speaker-Aware Modeling for Speech Separation

Fan-Lin Wang, Yu-Huai Peng, Hung-Shin Lee, Hsin-Min Wang

摘要:

近年来,语音分离被广泛研究以处理鸡尾酒会问题。所有相关的方法可以分为两类:时频域方法和时域方法。此外,一些方法尝试生成说话人向量以支持源分离。在这项研究中,我们提出了一个新的模型称为双路径过滤网络(DPFN)。我们的模型侧重于语音分离的后处理,以提高语音分离性能。DPFN由扬声器模块和分离模块两部分组成。首先,扬声器模块推断扬声器的身份。然后,分离模块使用说话者的信息从混合物中提取各个说话者的语音。基于DPRNN-TasNet构造的DPFN不仅优于DPRNN-TasNet,而且避免了置换不变训练(PIT)问题。

英文摘要:

Speech separation has been extensively studied to deal with the cocktail party problem in recent years. All related approaches can be divided into two categories: time-frequency domain methods and time domain methods. In addition, some methods try to generate speaker vectors to support source separation. In this study, we propose a new model called dual-path filter network (DPFN). Our model focuses on the post-processing of speech separation to improve speech separation performance. DPFN is composed of two parts: the speaker module and the separation module. First, the speaker module infers the identities of the speakers. Then, the separation module uses the speakers' information to extract the voices of individual speakers from the mixture. DPFN constructed based on DPRNN-TasNet is not only superior to DPRNN-TasNet, but also avoids the problem of permutation-invariant training (PIT).

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。

↑