Automatic Speech and Speaker Recognition

Dr Joseph Keshet, IDIAP, SwitzerlandDr Keshet received his B.Sc. and M.Sc. in electrical engineering from the Tel-Aviv University, Tel-Aviv, Israel, in 1994 and 2002, respectively. He got his Ph.D. from the Hebrew University of Jerusalem, Israel in 2007. From 1994 to 2002, he was with the Israeli Defense Forces (Intelligence Corps), where he was in charge of advanced research activities in the fields of speech coding. Since 2007, he is a research scientist in speech recognition at IDIAP Research Institute, Martigny, Switzerland.Dr Samy Bengio, Google, California, USDr Bengio received his M.Sc. and Ph.D. degrees in Computer Science from University of Montreal in 1989 and 1993 respectively. Between 1999 and 2006, he was a senior researcher in statistical machine learning at IDIAP Research Institute, where he supervised PhD students and postdoctoral fellows working on many areas of machine learning. He is the author/co-author of more than 160 international publications, including 30 journal papers. He has organized several international workshops (such as the MLMI series) and been in the organization committee of several well known conferences (such as NIPS). Since early 2007, he is a research scientist in machine learning at Google, in Mountain View, California.

• List of Contributors. Preface.I Foundations.1 Introduction (Samy Bengio and Joseph Keshet).1.1 The Traditional Approach to Speech Processing.1.2 Potential Problems of the Probabilistic Approach.1.3 Support Vector Machines for Binary Classification.1.4 Outline.References.2 Theory and Practice of Support Vector Machines Optimization (Shai Shalev-Shwartz and Nathan Srebo).2.1 Introduction.2.2 SVM and L2-regularized Linear Prediction.2.3 Optimization Accuracy From a Machine Learning Perspective.2.4 Stochastic Gradient Descent.2.5 Dual Decomposition Methods.2.6 Summary.References.3 From Binary Classification to Categorial Prediction (Koby Crammer).3.1 Multi-category Problems.3.2 Hypothesis Class.3.3 Loss Functions.3.4 Hinge Loss Functions.3.5 A Generalized Perceptron Algorithm.3.6 A Generalized Passive–Aggressive Algorithm.3.7 A Batch Formulation.3.8 Concluding Remarks.3.9 Appendix. Derivations of the Duals of the Passive–Aggressive Algorithm and the Batch Formulation.References.II Acoustic Modeling.4 A Large Margin Algorithm for Forced Alignment (Joseph Keshet, Shai Shalev-Shwartz, Yoram Singer and Dan Chazan).4.1 Introduction.4.2 Problem Setting.4.3 Cost and Risk.4.4 A Large Margin Approach for Forced Alignment.4.5 An Iterative Algorithm.4.6 Efficient Evaluation of the Alignment Function.4.7 Base Alignment Functions.4.8 Experimental Results.4.9 Discussion.References.5 A Kernel Wrapper for Phoneme Sequence Recognition (Joseph Keshet and Dan Chazan).5.1 Introduction.5.2 Problem Setting.5.3 Frame-based Phoneme Classifier.5.4 Kernel-based Iterative Algorithm for Phoneme Recognition.5.5 Nonlinear Feature Functions.5.6 Preliminary Experimental Results.5.7 Discussion: Canwe Hope for Better Results?References.6 Augmented Statistical Models: Using Dynamic Kernels for Acoustic Models (Mark J. F. Gales).6.1 Introduction.6.2 Temporal Correlation Modeling.6.3 Dynamic Kernels.6.4 Augmented Statistical Models.6.5 Experimental Results.6.6 Conclusions.Acknowledgements.References.7 Large Margin Training of Continuous Density Hidden Markov Models (Fei Sha and Lawrence K. Saul).7.1 Introduction.7.2 Background.7.3 Large Margin Training.7.4 Experimental Results.7.5 Conclusion.References.III Language Modeling.8 A Survey of Discriminative Language Modeling Approaches for Large Vocabulary Continuous Speech Recognition (Brian Roark).8.1 Introduction.8.2 General Framework.8.3 Further Developments.8.4 Summary and Discussion.References.9 Large Margin Methods for Part-of-Speech Tagging (Yasemin Altun).9.1 Introduction.9.2 Modeling Sequence Labeling.9.3 Sequence Boosting.9.4 Hidden Markov Support Vector Machines.9.5 Experiments.9.6 Discussion.References.10 A Proposal for a Kernel Based Algorithm for Large Vocabulary Continuous Speech Recognition (Joseph Keshet).10.1 Introduction.10.2 Segment Models and Hidden Markov Models.10.3 Kernel Based Model.10.4 Large Margin Training.10.5 Implementation Details.10.6 Discussion.Acknowledgements.References.IV Applications.11 Discriminative Keyword Spotting (David Grangier, Joseph Keshet and Samy Bengio).11.1 Introduction.11.2 Previous Work.11.3 Discriminative Keyword Spotting.11.4 Experiments and Results.11.5 Conclusions.Acknowledgements.References.12 Kernel-based Text-independent Speaker Verification (Johnny Mariéthoz, Samy Bengio and Yves Grandvalet).12.1 Introduction.12.2 Generative Approaches.12.3 Discriminative Approaches.12.4 Benchmarking Methodology.12.5 Kernels for Speaker Verification.12.6 Parameter Sharing.12.7 Is the Margin Useful for This Problem?12.8 Comparing all Methods.12.9 Conclusion.References.13 Spectral Clustering for Speech Separation (Francis R. Bach and Michael I. Jordan).13.1 Introduction.13.2 Spectral Clustering and Normalized Cuts.13.3 Cost Functions for Learning the Similarity Matrix.13.4 Algorithms for Learning the Similarity Matrix.13.5 Speech Separation as Spectrogram Segmentation.13.6 Spectral Clustering for Speech Separation.13.7 Conclusions.References .Index.