Keshet / Bengio Automatic Speech and Speaker Recognition

Large Margin and Kernel Methods
1. Auflage 2009
ISBN: 978-0-470-74203-7
Verlag: John Wiley & Sons
Format: PDF
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)

E-Book, Englisch, 268 Seiten, E-Book

This book discusses large margin and kernel methods for speechand speaker recognition

Speech and Speaker Recognition: Large Margin and KernelMethods is a collation of research in the recent advances inlarge margin and kernel methods, as applied to the field of speechand speaker recognition. It presents theoretical and practicalfoundations of these methods, from support vector machines to largemargin methods for structured learning. It also provides examplesof large margin based acoustic modelling for continuous speechrecognizers, where the grounds for practical large margin sequencelearning are set. Large margin methods for discriminative languagemodelling and text independent speaker verification are alsoaddressed in this book.

Key Features:

* Provides an up-to-date snapshot of the current state ofresearch in this field

* Covers important aspects of extending the binary support vectormachine to speech and speaker recognition applications

* Discusses large margin and kernel method algorithms forsequence prediction required for acoustic modeling

* Reviews past and present work on discriminative training oflanguage models, and describes different large margin algorithmsfor the application of part-of-speech tagging

* Surveys recent work on the use of kernel approaches totext-independent speaker verification, and introduces the mainconcepts and algorithms

* Surveys recent work on kernel approaches to learning asimilarity matrix from data

This book will be of interest to researchers, practitioners,engineers, and scientists in speech processing and machine learningfields.

Autoren/Hrsg.

Keshet, Joseph

Bengio, Samy

Über Autor(innen)

Dr Joseph Keshet, IDIAP, Switzerland
Dr Keshet received his B.Sc. and M.Sc. in electricalengineering from the Tel-Aviv University, Tel-Aviv, Israel, in 1994and 2002, respectively. He got his Ph.D. from the Hebrew Universityof Jerusalem, Israel in 2007. From 1994 to 2002, he was with theIsraeli Defense Forces (Intelligence Corps), where he was in chargeof advanced research activities in the fields of speech coding.Since 2007, he is a research scientist in speech recognition atIDIAP Research Institute, Martigny, Switzerland.Dr Samy Bengio, Google, California, US
Dr Bengio received his M.Sc. and Ph.D. degrees in ComputerScience from University of Montreal in 1989 and 1993 respectively.Between 1999 and 2006, he was a senior researcher in statisticalmachine learning at IDIAP Research Institute, where he supervisedPhD students and postdoctoral fellows working on many areas ofmachine learning. He is the author/co-author of more than 160international publications, including 30 journal papers. He hasorganized several international workshops (such as the MLMI series)and been in the organization committee of several well knownconferences (such as NIPS). Since early 2007, he is a researchscientist in machine learning at Google, in Mountain View,California.