Deep Learning for Environmentally Robust Speech Recognition

By Zixing Zhang, Jürgen T. Geiger, Jouni Pohjalainen, Amr El-Desoky Mousa, Björn Schuller. ACM Transactions on Intelligent Systems and Technology, 2017

344 citations recorded by the source corpus.

Eliminating the negative effect of non-stationary environmental noise is a long-standing research topic for automatic speech recognition but still remains an important challenge. Data-driven supervised approaches, especially the 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. In the meanwhile, we discuss the pros and cons of these approaches and provide their experimental results on benchmark databases. We expect that this overview can facilitate the development of the robustness of speech recognition systems in acoustic noisy environments.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/b06f2a7460bef1c1ef48c7c3353dbcc864727cc2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Chunwei Tian
2. Wangmeng Zuo
3. D. Bull
4. Nantheera Anantrasirichai
5. Lunke Fei
6. Chia-Wen Lin
7. Yong Xu
8. Wenxian Zheng

In Signal Processing

1. Wangmeng Zuo
2. D. Bull
3. Nantheera Anantrasirichai
4. Yong Xu

Citations in the corpus

• Artificial intelligence in the creative industries: a review (2020, methodology): “RNNs have been employed successfully to remove noise in audio [136, 137].”
• Deep Learning on Image Denoising: An overview (2019, positive): “After that, deep network architectures (e.g., VGG [189] and GoogLeNet [196]) were widely applied in the fields of image [225, 217, 119], video [138, 248], nature language processing [52] and speech processing [267], especially low-level computer vision [169, 204].”