Robust Automatic Speech Recognition

Chapter 3

Background of robust speech recognition

Abstract

In this chapter, we establish some fundamental concepts that are most relevant to the discussions in the remainder of this book. We first model distortions of speech in acoustic environments. We show how noise impacts Gaussian models and explain why deep neural network (DNN) models are more robust to noise. We then formulate a general framework for noise-robust ASR as the foundation of a wide variety of techniques presented in the remainder of this book. Based on the general framework described in this chapter, we provide a comprehensive overview, in a mathematically rigorous and unified manner, of noise-robust ASR using five different ways of categorizing, analyzing, and characterizing ...