arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.03065cs.SDeess.AS
收藏

未知说话人数目的递归语音分离

Recursive speech separation for unknown number of speakers

Naoya Takahashi, Sudarsanam Parthasaarathy, Nabarun Goswami, Yuki Mitsufuji

摘要:

本文提出了一种未知说话人数目的单通道非特定人多说话人语音分离方法。相对于以前的作品,其中的扬声器的数量被假定为是已知的提前和语音分离模型是特定的扬声器的数量,我们所提出的方法可以应用于不同数量的扬声器使用一个单一的模型,通过递归分离扬声器的情况。为了使分离模型递归适用,我们提出了一个和其余的排列不变训练(OR-PIT)。WSJ 0 - 2 mix和WSJ 0 - 3 mix数据集上的评估表明,我们提出的方法实现了最先进的结果,两个和三个扬声器混合与一个单一的模型。此外,相同的模型可以分离四个扬声器混合,这是在训练过程中从未见过的。我们进一步提出了在递归分离过程中检测混合物中的扬声器数量,并表明这种方法可以更准确地估计扬声器的数量比使用基于深度神经网络的分类器提前检测。

英文摘要:

In this paper we propose a method of single-channel speaker-independent multi-speaker speech separation for an unknown number of speakers. As opposed to previous works, in which the number of speakers is assumed to be known in advance and speech separation models are specific for the number of speakers, our proposed method can be applied to cases with different numbers of speakers using a single model by recursively separating a speaker. To make the separation model recursively applicable, we propose one-and-rest permutation invariant training (OR-PIT). Evaluation on WSJ0-2mix and WSJ0-3mix datasets show that our proposed method achieves state-of-the-art results for two- and three-speaker mixtures with a single model. Moreover, the same model can separate four-speaker mixture, which was never seen during the training. We further propose the detection of the number of speakers in a mixture during recursive separation and show that this approach can more accurately estimate the number of speakers than detection in advance by using a deep neural network based classifier.

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。

↑