The Application of Hidden Markov Models in Speech Recognition presents the core architecture of a HMM-based LVCSR system and proceeds to describe the various refinements which are needed to achieve state-of-the-art performance.

The book provides an up-to-date and authoritative treatment of pattern recognition and computer vision, with chapters written by leaders in the field. On the basic methods in pattern recognition and computer vision, topics range from statistical pattern recognition to array grammars to projective geometry to skeletonization, and shape and texture measures. Recognition applications include character recognition and document analysis, detection of digital mammograms, remote sensing image fusion, and analysis of functional magnetic resonance imaging data, etc. There are six chapters on current activities in human identification. Other topics include moving object tracking, performance evaluation, content-based video analysis, musical style recognition, number plate recognition, etc.

Proceedings of the NATO Advanced Study Institute on Computational Models of Speech Pattern Processing, held in St. Helier, Jersey, UK, July 7-18, 1997

After decades of research activity, Chinese spoken language processing (CSLP) has advanced considerably both in practical technology and theoretical discovery. In this book, the editors provide both an introduction to the field as well as unique research problems with their solutions in various areas of CSLP. The contributions represent pioneering efforts ranging from CSLP principles to technologies and applications, with each chapter encapsulating a single problem and its solutions.A commemorative volume for the 10th anniversary of the international symposium on CSLP in Singapore, this is a valuable reference for established researchers and an excellent introduction for those interested in the area of CSLP.

In this book, we introduce the background and mainstream methods of probabilistic modeling and discriminative parameter optimization for speech recognition. The specific models treated in depth include the widely used exponential-family distributions and the hidden Markov model. A detailed study is presented on unifying the common objective functions for discriminative learning in speech recognition, namely maximum mutual information (MMI), minimum classification error, and minimum phone/word error. The unification is presented, with rigorous mathematical analysis, in a common rational-function form. This common form enables the use of the growth transformation (or extended Baum-Welch) optimization framework in discriminative learning of model parameters. In addition to all the necessary introduction of the background and tutorial material on the subject, we also included technical details on the derivation of the parameter optimization formulas for exponential-family distributions, discrete hidden Markov models (HMMs), and continuous-density HMMs in discriminative learning. Selected experimental results obtained by the authors in firsthand are presented to show that discriminative learning can lead to superior speech recognition performance over conventional parameter learning. Details on major algorithmic implementation issues with practical significance are provided to enable the practitioners to directly reproduce the theory in the earlier part of the book into engineering practice.

In this book, we introduce the background and mainstream methods of probabilistic modeling and discriminative parameter optimization for speech recognition. The specific models treated in depth include the widely used exponential-family distributions and the hidden Markov model. A detailed study is presented on unifying the common objective functions for discriminative learning in speech recognition, namely maximum mutual information (MMI), minimum classification error, and minimum phone/word error. The unification is presented, with rigorous mathematical analysis, in a common rational-function form. This common form enables the use of the growth transformation (or extended Baum–Welch) optimization framework in discriminative learning of model parameters. In addition to all the necessary introduction of the background and tutorial material on the subject, we also included technical details on the derivation of the parameter optimization formulas for exponential-family distributions, discrete hidden Markov models (HMMs), and continuous-density HMMs in discriminative learning. Selected experimental results obtained by the authors in firsthand are presented to show that discriminative learning can lead to superior speech recognition performance over conventional parameter learning. Details on major algorithmic implementation issues with practical significance are provided to enable the practitioners to directly reproduce the theory in the earlier part of the book into engineering practice. Table of Contents: Introduction and Background / Statistical Speech Recognition: A Tutorial / Discriminative Learning: A Unified Objective Function / Discriminative Learning Algorithm for Exponential-Family Distributions / Discriminative Learning Algorithm for Hidden Markov Model / Practical Implementation of Discriminative Learning / Selected Experimental Results / Epilogue / Major Symbols Used in the Book and Their Descriptions / Mathematical Notation / Bibliography