Robust Automatic Speech Recognition
A Bridge to Practical Applications

Learn how automatic speech recognition can be used with robustness in real-world applications

Jinyu Li (Author), Li Deng (Author), Reinhold Haeb-Umbach (Author), Yifan Gong (Author)

9780128023983, Elsevier Science

Hardback, published 14 October 2015

306 pages
23.4 x 19 x 2.3 cm, 0.79 kg

Robust Automatic Speech Recognition: A Bridge to Practical Applications establishes a solid foundation for automatic speech recognition that is robust against acoustic environmental distortion. It provides a thorough overview of classical and modern noise-and reverberation robust techniques that have been developed over the past thirty years, with an emphasis on practical methods that have been proven to be successful and which are likely to be further developed for future applications.The strengths and weaknesses of robustness-enhancing speech recognition techniques are carefully analyzed. The book covers noise-robust techniques designed for acoustic models which are based on both Gaussian mixture models and deep neural networks. In addition, a guide to selecting the best methods for practical applications is provided.The reader will:

1. Introduction
2. Fundamental of speech recognition
3. Background of robust speech recognition
4. Processing in the Feature and Model Domains
5. Compensation with prior knowledge
6. Explicit distortion modeling
7. Uncertainty processing
8. Joint model training
9. Reverberant speech recognition
10. Multi-channel processing
11. Summary and Future Directions

Subject Areas: Acoustic & sound engineering [TTA], Electronics & communications engineering [TJ], Mechanical engineering [TGB]