Preliminaries

Shinji Watanabe, Marc Delcroix, Florian Metze, John R. HersheyNew Era for Robust Speech Recognition, Exploiting Deep Learning 2017 · OpenReview

Abstract

Robust automatic speech recognition (ASR) technologies have greatly evolved due to the emergence of deep learning. This chapter introduces the general background of robustness issues of deep neural-network-based ASR. It provides an overview of robust ASR research including a brief history of several studies before the deep learning era, basic formulations of ASR, signal processing, and neural networks. This chapter also introduces common notations for variables and equations, which are extended in the later chapters to deal with more advanced topics. Finally, the chapter provides an overview of the book structure by summarizing the contributions of the individual chapters and associates them with the different components of a robust ASR system.
BibTeX
@inproceedings{watanabe2017preliminaries,
  author = {Shinji Watanabe and Marc Delcroix and Florian Metze and John R. Hershey},
  title = {{Preliminaries}},
  booktitle = {New Era for Robust Speech Recognition, Exploiting Deep Learning},
  year = {2017},
  url = {https://openreview.net/forum?id=lyIFHnyfoPu},
}

Loading related content...

Figure