arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.09081cs.SDeess.AS
收藏

基于深度复Unet的多通道自动语音识别

Multi-Channel Automatic Speech Recognition Using Deep Complex Unet

Northwestern Polytechnical University(西北工业大学);Xiaomi Inc.(小米公司)

Yuxiang Kong, Jian Wu, Quandong Wang, Peng Gao, Weiji Zhuang, Yujun Wang, Lei Xie

摘要:

多通道自动语音识别(ASR)系统的前端模块主要利用麦克风阵列技术在混响和回声等噪声条件下产生增强信号。最近,基于神经网络(NN)的前端已经显示出比传统的信号处理方法有前途的改进。在本文中,我们建议采用深度复杂Unet(DCUnet)的架构-一个强大的复值Unet结构的语音增强模型-作为多通道声学模型的前端,并将它们集成在多任务学习(MTL)框架中,并与级联框架进行比较。同时,我们研究了所提出的方法与几种训练策略,以提高识别精度的1000小时的真实世界小米智能扬声器数据的回声。实验结果表明,与传统的阵列处理加单通道声学模型的方法相比,我们提出的DCUnet-MTL方法可以使相对特征出错率(CER)降低12.2%。它也实现了优于最近提出的神经波束形成方法的性能。

英文摘要:

The front-end module in multi-channel automatic speech recognition (ASR) systems mainly use microphone array techniques to produce enhanced signals in noisy conditions with reverberation and echos. Recently, neural network (NN) based front-end has shown promising improvement over the conventional signal processing methods. In this paper, we propose to adopt the architecture of deep complex Unet (DCUnet) - a powerful complex-valued Unet-structured speech enhancement model - as the front-end of the multi-channel acoustic model, and integrate them in a multi-task learning (MTL) framework along with cascaded framework for comparison. Meanwhile, we investigate the proposed methods with several training strategies to improve the recognition accuracy on the 1000-hours real-world XiaoMi smart speaker data with echos. Experiments show that our proposed DCUnet-MTL method brings about 12.2% relative character error rate (CER) reduction compared with the traditional approach with array processing plus single-channel acoustic model. It also achieves superior performance than the recently proposed neural beamforming method.

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。

↑