Polyteknisk Boghandel

Speech dereverberation is a signal processing technique of key importance for successful hands-free speech acquisition in applications of telecommunications and automatic speech recognition. Without dereverberation, the acoustic environment affects the speech signal by colouring its spectrum and giving an 'echo' to the sound. Such degradations render speech recognition unusable and substantially reduce speech intelligibility for telecommunication with hands-free speech acquisition. Over the last 2 to 3 years, speech dereverberation has become a hot topic of research driven by consumer demand, the availability of Skype-based and MSN-based terminals which encourage hands-free operation and the development of promising signal processing algorithms.Speech Dereverberation collects together, for the very first time in a single volume, an overview and a mathematical formulation of the problem and the state of the art solutions for dereverberation. After considering how dereverberation performance can be measured, the subsequent chapters present the current approaches within a unified framework. The background to the algorithms is explained, together with relevant mathematical analysis and supporting examples and simulations. Techniques rooted in speech enhancement are included. In addition, a substantial treatment of multichannel blind acoustic system identification is provided. System inversion and deconvolution is also covered. Furthermore, the book encourages further work on this topic by offering open research questions to exercise the curiosity of the reader.Speech Dereverberation is suitable for students at masters and doctoral level as well as established researchers in signal processing, telecommunications, speech recognition and related industries.