Advertisement

Blind Speech Separation

  • Shoji Makino
  • Hiroshi Sawada
  • Te-Won Lee

Part of the Signals and Communication Technology book series (SCT)

Table of contents

  1. Front Matter
    Pages I-XV
  2. Multiple Microphone Blind Speech Separation with ICA

    1. Front Matter
      Pages 1-1
    2. Scott C. Douglas, Malay Gupta
      Pages 3-45
    3. Shoji Makino, Hiroshi Sawada, Shoko Araki
      Pages 47-78
    4. Mike Davies, Maria Jafari, Samer Abdallah, Emmanuel Vincent, Mark Plumbley
      Pages 79-99
    5. Hiroshi Saruwatari, Tomoya Takatani, Kiyohiro Shikano
      Pages 149-168
    6. Intae Lee, Taesu Kim, Te-Won Lee
      Pages 169-192
  3. Underdetermined Blind Speech Separation with Sparseness

    1. Front Matter
      Pages 215-215
    2. Scott Rickard
      Pages 217-241
    3. Shoko Araki, Hiroshi Sawada, Shoji Makino
      Pages 243-270
    4. Stefan Winter, Walter Kellermann, Hiroshi Sawada, Shoji Makino
      Pages 271-304
    5. Cédric Févotte
      Pages 305-335
  4. Single Microphone Blind Speech Separation

    1. Front Matter
      Pages 337-337
    2. Gil-Jin Jang, Te-Won Lee
      Pages 339-364
    3. Hiroki Asari, Rasmus K. Olsson, Barak A. Pearlmutter, Anthony M. Zador
      Pages 387-410
  5. Back Matter
    Pages 429-432

About this book

Introduction

This is the first book to provide a cutting edge reference to the fascinating topic of blind source separation (BSS) for convolved speech mixtures. Through contributions by the foremost experts on the subject, the book provides an up-to-date account of research findings, explains the underlying theory, and discusses potential applications. The individual chapters are designed to be tutorial in nature with specific emphasis on an in-depth treatment of state of the art techniques.

Blind Speech Separation is divided into three parts:

Part 1 presents overdetermined or critically determined BSS. Here the main technology is independent component analysis (ICA). ICA is a statistical method for extracting mutually independent sources from their mixtures. This approach utilizes spatial diversity to discriminate between desired and undesired components, i.e., it reduces the undesired components by forming a spatial null towards them. It is, in fact, a blind adaptive beamformer realized by unsupervised adaptive filtering.

Part 2 addresses underdetermined BSS, where there are fewer microphones than source signals. Here, the sparseness of speech sources is very useful; we can utilize time-frequency diversity, where sources are active in different regions of the time-frequency plane.

Part 3 presents monaural BSS where there is only one microphone. Here, we can separate a mixture by using the harmonicity and temporal structure of the sources. We can build a probabilistic framework by assuming a source model, and separate a mixture by maximizing the a posteriori probability of the sources.

Keywords

Independent Component Analysis Support Vector Machine adaptive Filter algorithm algorithms blind source separation clustering filtering filters optimization sparse component analysis system identification unsupervised learning

Editors and affiliations

  • Shoji Makino
    • 1
  • Hiroshi Sawada
    • 1
  • Te-Won Lee
    • 2
  1. 1.NTT CorporationSoraku-gunJapan
  2. 2.University of California, San DiegoLa JollaUSA

Bibliographic information

  • DOI https://doi.org/10.1007/978-1-4020-6479-1
  • Copyright Information Springer Science+Business Media B.V. 2007
  • Publisher Name Springer, Dordrecht
  • eBook Packages Engineering
  • Print ISBN 978-1-4020-6478-4
  • Online ISBN 978-1-4020-6479-1
  • Series Print ISSN 1860-4862
  • Buy this book on publisher's site