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 which are most
reliable for recognition.
This book presents the state of the art in recognition of uncertain or missing
speech data, presenting examples that utilize uncertainty information for noise robustness,
for reverberation robustness and for the simultaneous recognition of multiple
speech signals, as well as for audiovisual speech recognition.
The editors thank all the authors for their valuable contributions and their cooperation
in unifying the layout of the book and the terminology and symbols used. It
was a great pleasure working with all of them!
Furthermore, the editors would like to express their gratitude to Ronan Nugent
of Springer for his encouragement and support during the creation of this book.We
also thank Alexander Krueger and Volker Leutnant for their help with the compilation
of the LaTeX document.