Multi-Channel Automatic Speech Recognition Using Deep Complex Unet
This work provides a significant improvement in speech recognition accuracy for smart speaker users experiencing noisy and echo-prone environments, especially for the XiaoMi platform.
This paper addresses the challenge of multi-channel automatic speech recognition (ASR) in noisy environments with reverberation and echoes. The authors propose using a deep complex Unet (DCUnet) as the front-end in a multi-task learning (MTL) framework, achieving a 12.2% relative character error rate (CER) reduction on 1000 hours of real-world XiaoMi smart speaker data compared to traditional array processing.
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.