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.
Author(s): Reinhold Haeb-Umbach, Dorothea Kolossa (auth.), Dorothea Kolossa, Reinhold Häb-Umbach (eds.)
Edition: 1
Publisher: Springer-Verlag Berlin Heidelberg
Year: 2011
Language: English
Pages: 380
Tags: Signal, Image and Speech Processing; Artificial Intelligence (incl. Robotics); Computational Linguistics
Front Matter....Pages i-xviii
Introduction....Pages 1-5
Front Matter....Pages 7-7
Uncertainty Decoding and Conditional Bayesian Estimation....Pages 9-33
Uncertainty Propagation....Pages 35-64
Front Matter....Pages 65-65
Front-End, Back-End, and Hybrid Techniques for Noise-Robust Speech Recognition....Pages 67-99
Model-Based Approaches to Handling Uncertainty....Pages 101-125
Reconstructing Noise-Corrupted Spectrographic Components for Robust Speech Recognition....Pages 127-156
Automatic Speech Recognition Using Missing Data Techniques: Handling of Real-World Data....Pages 157-185
Conditional Bayesian Estimation Employing a Phase-Sensitive Observation Model for Noise Robust Speech Recognition....Pages 187-221
Front Matter....Pages 223-223
Variance Compensation for Recognition of Reverberant Speech with Dereverberation Preprocessing....Pages 225-255
A Model-Based Approach to Joint Compensation of Noise and Reverberation for Speech Recognition....Pages 257-290
Front Matter....Pages 291-291
Evidence Modeling for Missing Data Speech Recognition Using Small Microphone Arrays....Pages 293-318
Recognition of Multiple Speech Sources Using ICA....Pages 319-344
Use of Missing and Unreliable Data for Audiovisual Speech Recognition....Pages 345-375
Back Matter....Pages 377-380
