Progress in Nonlinear Speech Processing (Lecture Notes in Computer Science) (Paperback

Description

This book constitutes of the major results of the EU COST (European Cooperation in the field of Scientific and Technical Research) Action 277: NSP - Nonlinear Speech Processing - running from April 2001 to June 2005. The results were presented at the last meeting of the management committee of COST Action 277, held in Heraklion, Crete, Greece on September 20-23, 2005 during the Workshop on Nonlinear Speech Processing, WNSP 2005.

The 13 revised full papers in this state-of-the-art survey were carefully reviewed and selected for inclusion in the book and are preceded with an introductory leading-in by the editors. The articles present overviews of the four years research combining linear and non linear approaches for processing the speech signal. The aim of this book is to provide an additional and/or an alternative way to the traditional approach of linear speech processing and be mainly used by the researcher working in the domain. The papers cover areas such as speech analysis for speech synthesis, speech recognition, speech-non speech discrimination and voice quality assessment, speaker recognition/verification from a natural or modified speech signal, speech recognition, speech enhancement, and emotional state detection.

描述

本書是歐盟COST（歐洲科學與技術研究合作）行動277號：NSP（非線性語音處理）的主要成果，該行動從2001年4月至2005年6月進行。這些結果在COST行動277號管理委員會的最後一次會議上進行了介紹，該會議於2005年9月20日至23日在希臘克里特島的赫拉克利翁舉行，並在2005年非線性語音處理研討會（WNSP 2005）期間進行了介紹。

這本專題綜述中的13篇修訂完整論文經過仔細審查和選擇，並由編輯提供了引導性的前言。這些文章概述了四年的研究成果，結合了線性和非線性方法來處理語音信號。本書的目的是為研究該領域的研究人員提供一種額外和/或替代傳統的線性語音處理方法。這些論文涵蓋了語音分析、語音合成、語音識別、語音-非語音區分和語音質量評估、自然或修改語音信號的語音識別/驗證、語音增強和情感狀態檢測等領域。