New Era for Robust Speech Recognition Exploiting Deep Learning /

This book covers the state-of-the-art in deep neural-network-based methods for noise robustness in distant speech recognition applications. It provides insights and detailed descriptions of some of the new concepts and key technologies in the field, including novel architectures for speech enhanceme...

Full description

Bibliographic Details
Corporate Author: SpringerLink (Online service)
Other Authors: Watanabe, Shinji (Editor), Delcroix, Marc (Editor), Metze, Florian (Editor), Hershey, John R. (Editor)
Format: Electronic eBook
Language:English
Published: Cham : Springer International Publishing : Imprint: Springer, 2017.
Subjects:
Online Access:Full Text via HEAL-Link
Table of Contents:
  • Speech and Language Processing
  • Automatic Speech Recognition (ASR)
  • Recent Applications
  • Signal-Processing-Based Front-End for Robust ASR
  • Generative Model-Based Speech Enhancement
  • Denoising Autoencoder
  • Discriminative Microphone Array Enhancement
  • Learning Robust Feature Representation
  • Training Data Augmentation
  • Adaptation and Augmented Features
  • Novel Model Topologies
  • Novel Objective Criteria
  • Benchmark Data, Tools, and Systems.