Automatic Speech and Speaker Recognition: Large Margin and Kernel Methods
"This book discusses large margin and kernel methods for speech and speaker recognition." Automatic Speech and Speaker Recognition: Large Margin and Kernel Methods is a collation of research in the recent advances in large margin and kernel methods, as applied to the field of speech and speaker recognition. It presents theoretical and practical foundations of these methods, from support vector machines to large margin methods for structured learning. It also provides examples of large margin...
Search in google:
This book discusses large margin and kernel methods for speech and speaker recognition Speech and Speaker Recognition: Large Margin and Kernel Methods is a collation of research in the recent advances in large margin and kernel methods, as applied to the field of speech and speaker recognition. It presents theoretical and practical foundations of these methods, from support vector machines to large margin methods for structured learning. It also provides examples of large margin based acoustic modelling for continuous speech recognizers, where the grounds for practical large margin sequence learning are set. Large margin methods for discriminative language modelling and text independent speaker verification are also addressed in this book. Key Features:Provides an up-to-date snapshot of the current state of research in this fieldCovers important aspects of extending the binary support vector machine to speech and speaker recognition applicationsDiscusses large margin and kernel method algorithms for sequence prediction required for acoustic modelingReviews past and present work on discriminative training of language models, and describes different large margin algorithms for the application of part-of-speech taggingSurveys recent work on the use of kernel approaches to text-independent speaker verification, and introduces the main concepts and algorithmsSurveys recent work on kernel approaches to learning a similarity matrix from data This book will be of interest to researchers, practitioners, engineers, and scientists in speech processing and machine learning fields.
I Foundations 11 Introduction Samy Bengio Bengio, Samy Joseph Keshet Keshet, Joseph 32 Theory and Practice of Support Vector Machines Optimization Shai Shalev-Shwartz Shalev-Shwartz, Shai Nathan Srebo Srebo, Nathan 113 From Binary Classification to Categorial Prediction Koby Crammer Crammer, Koby 27II Acoustic Modeling 514 A Large Margin Algorithm for Forced Alignment Joseph Keshet Keshet, Joseph Shai Shalev-Shwartz Shalev-Shwartz, Shai Yomm Singer Singer, Yomm Dan Chazan Chazan, Dan 535 A Kernel Wrapper for Phoneme Sequence Recognition Joseph Keshet Keshet, Joseph Dan Chazan Chazan, Dan 696 Augmented Statistical Models: Using Dynamic Kernels for Acoustic Models Mark J. F. Gales Gales, Mark J. F. 837 Large Margin Training of Continuous Density Hidden Markov Models Fei Sha Fei, Sha Lawrence K. Saul Saul, Lawrence K. 101III Language Modeling 1158 A Survey of Discriminative Language Modeling Approaches for Large Vocabulary Continuous Speech Recognition Brian Roark Roark, Brian 1179 Large Margin Methods for Part-of-Speech Tagging Yasemin Altun Altun, Yasemin 13910 A Proposal for a Kernel Based Algorithm for Large Vocabulary Continuous Speech Recognition Joseph Keshet Keshet, Joseph 159IV Applications 17311 Discriminative Keyword Spotting David Grangier Grangier, David Joseph Keshet Keshet, Joseph Samy Bengio Bengio, Samy 17512 Kernel-based Text-independent Speaker Verification Johnny Mariethoz Mariethoz, Johnny Samy Bengio Bengio, Samy Yves Grandvalet Grandvalet, Yves 19513 Spectral Clustering for Speech Separation Francis R. Bach Bach, Francis R. Michael I. Jordan Jordan, Michael I. 221Index 251
