增强混响作为无监督语音分离的监督
Enhanced Reverberation as Supervision for Unsupervised Speech Separation
AI总结：
本文提出增强混响作为监督（ERAS），通过缓解频率置换问题并引入伪目标损失项，在确定的声源-通道条件下实现稳定的无监督单声道语音分离。
摘要：
混响作为监督（RAS）是一种允许以无监督方式从多通道混合信号训练单声道语音分离模型的框架。在RAS中，模型经过训练，使从输入通道的混合信号中预测出的声源能够被映射以重建目标通道处的混合信号。然而，迄今为止，稳定的无监督训练仅在超定的声源-通道条件下实现，关键的确定情形仍未解决。本工作提出增强RAS（ERAS）来解决这一问题。通过定性分析，我们发现利用损失项来缓解频率置换问题可以实现稳定训练。通过添加一个新的损失项，分离性能也得到提升，在该损失项中，映射回其自身输入混合信号的分离信号被用作伪目标，用于从其他通道分离并映射到同一通道的信号。实验结果表明ERAS具有高稳定性和高性能。
英文摘要：
Reverberation as supervision (RAS) is a framework that allows for training monaural speech separation models from multi-channel mixtures in an unsupervised manner. In RAS, models are trained so that sources predicted from a mixture at an input channel can be mapped to reconstruct a mixture at a target channel. However, stable unsupervised training has so far only been achieved in over-determined source-channel conditions, leaving the key determined case unsolved. This work proposes enhanced RAS (ERAS) for solving this problem. Through qualitative analysis, we found that stable training can be achieved by leveraging the loss term to alleviate the frequency-permutation problem. Separation performance is also boosted by adding a novel loss term where separated signals mapped back to their own input mixture are used as pseudo-targets for the signals separated from other channels and mapped to the same channel. Experimental results demonstrate high stability and performance of ERAS.
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。
