CNN-based MultiChannel End-to-End Speech Recognition for everyday home environments

Abstract

Casual conversations involving multiple speakers and noises from surrounding devices are common in everyday environments, which degrades the performances of automatic speech recognition systems. These challenging characteristics of environments are the target of the CHiME-5 challenge. By employing a convolutional neural network (CNN)-based multichannel end-to-end speech recognition system, this study attempts to overcome the presents difficulties in everyday environments. The system comprises of an attention-based encoder-decoder neural network that directly generates a text as an output from a sound input. The multichannel CNN encoder, which uses residual connections and batch renormalization, is trained with augmented data, including white noise injection. The experimental results show that the word error rate is reduced by 8.5% and 0.6% absolute from a single channel end-to-end and the best baseline (LF-MMI TDNN) on the CHiME-5 corpus, respectively.

arXiv comment5 pages, 1 figure, EUSIPCO 2019

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• ADADELTA: An Adaptive Learning Rate Method
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• Attention-Based Models for Speech Recognition
• End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results
• Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models
• Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning