arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.03889eess.AScs.SD
收藏

用于目标语音分离的神经时空波束形成器

Neural Spatio-Temporal Beamformer for Target Speech Separation

Tencent AI Lab(腾讯人工智能实验室)

Yong Xu, Meng Yu, Shi-Xiong Zhang, Lianwu Chen, Chao Weng, Jianming Liu, Dong Yu

摘要:

基于神经网络的语音分离和增强方法虽然能取得较好的客观效果,但不可避免地会产生非线性语音失真,这对自动语音识别(ASR)是有害的。另一方面,最小方差无失真响应(MVDR)波束形成器与NN预测的面具,虽然可以显着减少语音失真,具有有限的降噪能力。在本文中,我们提出了一个多抽头MVDR波束形成器与复值掩模语音分离和增强。与现有技术的基于NN掩模的MVDR波束形成器相比,除了现有技术中已经利用的麦克风间相关性之外,多抽头MVDR波束形成器还利用帧间相关性。进一步的改进包括用复值掩码替换实值掩码和复掩码NN的联合训练。对我们的多模态多通道目标语音分离和增强平台的评估表明,我们提出的多抽头MVDR波束形成器相对于现有技术提高了ASR准确性和感知语音质量。

英文摘要:

Purely neural network (NN) based speech separation and enhancement methods, although can achieve good objective scores, inevitably cause nonlinear speech distortions that are harmful for the automatic speech recognition (ASR). On the other hand, the minimum variance distortionless response (MVDR) beamformer with NN-predicted masks, although can significantly reduce speech distortions, has limited noise reduction capability. In this paper, we propose a multi-tap MVDR beamformer with complex-valued masks for speech separation and enhancement. Compared to the state-of-the-art NN-mask based MVDR beamformer, the multi-tap MVDR beamformer exploits the inter-frame correlation in addition to the inter-microphone correlation that is already utilized in prior arts. Further improvements include the replacement of the real-valued masks with the complex-valued masks and the joint training of the complex-mask NN. The evaluation on our multi-modal multi-channel target speech separation and enhancement platform demonstrates that our proposed multi-tap MVDR beamformer improves both the ASR accuracy and the perceptual speech quality against prior arts.

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。

↑