Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developments
arXiv:1705.10874
Abstract
Eliminating the negative effect of non-stationary environmental noise is a long-standing research topic for automatic speech recognition that stills remains an important challenge. Data-driven supervised approaches, including ones based on deep neural networks, have recently emerged as potential alternatives to traditional unsupervised approaches and with sufficient training, can alleviate the shortcomings of the unsupervised methods in various real-life acoustic environments. In this light, we review recently developed, representative deep learning approaches for tackling non-stationary additive and convolutional degradation of speech with the aim of providing guidelines for those involved in the development of environmentally robust speech recognition systems. We separately discuss single- and multi-channel techniques developed for the front-end and back-end of speech recognition systems, as well as joint front-end and back-end training frameworks.
References in corpus (10)
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Generative Adversarial Networks: An Overview
- WaveNet: A Generative Model for Raw Audio
- Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
- Wide Residual Networks
- Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
- On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
- Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation
- Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification
- Deep Long Short-Term Memory Adaptive Beamforming Networks For Multichannel Robust Speech Recognition