Robust Speech Recognition of Uncertain or Missing Data

Theory and Applications

By Dorothea Kolossa , Reinhold Haeb-Umbach

Robust Speech Recognition of Uncertain or Missing Data Cover Image

This book presents the state of the art in recognition in the presence of uncertainty, offering examples that utilize uncertainty information for noise robustness, reverberation robustness, simultaneous recognition of multiple speech signals, and audiovisual speech recognition.

Full Description

  • ISBN13: 978-3-6422-1316-8
  • 394 Pages
  • User Level: Science
  • Publication Date: July 14, 2011
  • Available eBook Formats: PDF
  • eBook Price: $129.00
Buy eBook Buy Print Book Add to Wishlist
Full Description
Automatic speech recognition suffers from a lack of robustness with respect to noise, reverberation and interfering speech. The growing field of speech recognition in the presence of missing or uncertain input data seeks to ameliorate those problems by using not only a preprocessed speech signal but also an estimate of its reliability to selectively focus on those segments and features that are most reliable for recognition. This book presents the state of the art in recognition in the presence of uncertainty, offering examples that utilize uncertainty information for noise robustness, reverberation robustness, simultaneous recognition of multiple speech signals, and audiovisual speech recognition.The book is appropriate for scientists and researchers in the field of speech recognition who will find an overview of the state of the art in robust speech recognition, professionals working in speech recognition who will find strategies for improving recognition results in various conditions of mismatch, and lecturers of advanced courses on speech processing or speech recognition who will find a reference and a comprehensive introduction to the field. The book assumes an understanding of the fundamentals of speech recognition using Hidden Markov Models.
Table of Contents

Table of Contents

  1. Chap. 1 – Introduction.
  2. Part I – Theoretical Foundations.
  3. Chap. 2 – Uncertainty Decoding and Conditional Bayesian Estimation.
  4. Chap. 3 – Uncertainty Propagation.
  5. Part II – Applications.
  6. Chap. 4 – Front
  7. End, Back
  8. End, and Hybrid Techniques for Noise
  9. Robust Speech Recognition.
  10. Chap. 5 – Model
  11. Based Approaches to Handling Uncertainty.
  12. Chap. 6 – Reconstructing Noise
  13. Corrupted Spectrographic Components for Robust Speech Recognition.
  14. Chap. 7 – Automatic Speech Recognition Using Missing Data Techniques: Handling of Real
  15. World Data.
  16. Chap. 8 – Conditional Bayesian Estimation Employing a Phase
  17. Sensitive Estimation Model for Noise
  18. Robust Speech Recognition.
  19.   Part III – Reverberation Robustness.
  20. Chap. 9 – Variance Compensation for Recognition of Reverberant Speech with Dereverberation Processing.
  21. Chap. 10 – A Model
  22. Based Approach to Joint Compensation of Noise and Reverberation for Speech Recognition.
  23. Part IV – Applications: Multiple Speakers and Modalities.
  24. Chap. 11 – Evidence Modelling for Missing Data Speech Recognition Using Small Microphone Arrays.
  25. Chap. 12 – Recognition of Multiple Speech Sources Using ICA.
  26.  Chap. 13 – Use of Missing and Unreliable Data for Audiovisual Speech Recognition.
  27.   Index.
Errata

Please Login to submit errata.

No errata are currently published