Most speech separation methods, trying to separate all channel sources simultaneously, are still far from having enough general- ization capabilities for real scenarios where the number of input sounds is usually uncertain and even dynamic. In this work, we employ ideas from auditory attention with two ears and propose a speaker and direction inferred speech separation network (dubbed SDNet) to solve the cocktail party problem. Specifically, our SDNet first parses out the respective perceptual representations with their speaker and direction characteristics from the mixture of the scene in a sequential manner. Then, the perceptual representations are utilized to attend to each corresponding speech. Our model gener- ates more precise perceptual representations with the help of spatial features and successfully deals with the problem of the unknown number of sources and the selection of outputs. The experiments on standard fully-overlapped speech separation benchmarks, WSJ0- 2mix, WSJ0-3mix, and WSJ0-2&3mix, show the effectiveness, and our method achieves SDR improvements of 25.31 dB, 17.26 dB, and 21.56 dB under anechoic settings. Our codes will be released at https://github.com/aispeech-lab/SDNet.


翻译:多数语音分离方法试图同时将所有频道来源分开,但对于输入声音的数量通常不确定甚至动态的实际情况,大多数语音分离方法还远远没有达到足够的一般化能力。在这项工作中,我们采用两耳听觉关注的想法,并提议一个语音和导导导导导分离网络(dubbbed SDNet)来解决鸡尾酒问题。具体地说,我们的SDNet首先以顺序方式将各自的感知表达和声音和方向特点与场景的混合物区分开来。然后,利用感知表达方式来出席每次相应的演讲。我们的模型基因组在空间特征的帮助下,以更精确的感知表达方式处理未知的来源数量和产出选择的问题。关于标准超载语音分离基准、WSWJ0-2mix、WSJ0-3mix和WSJ0-2和3mix的实验将展示其有效性,我们的方法将STDR改进25.31 dB、17.26 dB和21.56 dB,并在有感知性的环境中,我们的代码将在 https://gibla/SDIS/SD.

0
下载
关闭预览

相关内容

Hierarchically Structured Meta-learning
CreateAMind
27+阅读 · 2019年5月22日
轻量级.NET Core快速开发框架OsharpNS
DotNet
3+阅读 · 2019年4月27日
Disentangled的假设的探讨
CreateAMind
9+阅读 · 2018年12月10日
disentangled-representation-papers
CreateAMind
26+阅读 · 2018年9月12日
Hierarchical Imitation - Reinforcement Learning
CreateAMind
19+阅读 · 2018年5月25日
Hierarchical Disentangled Representations
CreateAMind
4+阅读 · 2018年4月15日
Arxiv
8+阅读 · 2018年11月27日
VIP会员
相关VIP内容
Top
微信扫码咨询专知VIP会员