Connectionist Speech Recognition: A Hybrid Approach describes the theory and implementation of a method to incorporate neural network approaches into state of the art continuous speech recognition systems based on hidden Markov models (HMMs) to improve their performance. In this framework, neural networks (and in particular, multilayer perceptrons or MLPs) have been restricted to well-defined subtasks of the whole system, i.e. HMM emission probability estimation and feature extraction. The book describes a successful five-year international collaboration between the authors. The lessons learned form a case study that demonstrates how hybrid systems can be developed to combine neural networks with more traditional statistical approaches. The book illustrates both the advantages and limitations of neural networks in the framework of a statistical systems. Using standard databases and comparison with some conventional approaches, it is shown that MLP probability estimation can improve recognition performance. Other approaches are discussed, though there is no such unequivocal experimental result for these methods. Connectionist Speech Recognition is of use to anyone intending to use neural networks for speech recognition or within the framework provided by an existing successful statistical approach. This includes research and development groups working in the field of speech recognition, both with standard and neural network approaches, as well as other pattern recognition and/or neural network researchers. The book is also suitable as a text for advanced courses on neural networks or speech processing.

Connectionist accounts of language acquisition, processing, and dissolution proliferate despite attacks from some linguists, cognitive scientists, and engineers. Although the networks of exquisitely interconnected perceptrons postulated by PDP theorists may not be anatomically homologous with actual brain anatomy, a growing body of research suggests that the posited network functions can support many human behaviors. This volume brings together contributors with a variety of backgrounds and perspectives to explore, for the first time, the clinical implications of whole-language connectionist models. Demonstrating that these models are powerful and have explained many phenomena of language acquisition, language therapy, and speech processing, especially at the engineering level, they focus specifically on applications of connectionist theory to delayed language, aphasia, phonological acquisition, and speech perception. Connectionist models, they conclude, offer a new interpretive framework for the discussion of information processing in humans and other animals that will be of great utility to all those who study language and seek to intervene in language disorders.

Connection science is a new information-processing paradigm which attempts to imitate the architecture and process of the brain, and brings together researchers from disciplines as diverse as computer science, physics, psychology, philosophy, linguistics, biology, engineering, neuroscience and AI. Work in Connectionist Natural Language Processing (CNLP) is now expanding rapidly, yet much of the work is still only available in journals, some of them quite obscure. To make this research more accessible this book brings together an important and comprehensive set of articles from the journal CONNECTION SCIENCE which represent the state of the art in Connectionist natural language processing; from speech recognition to discourse comprehension. While it is quintessentially Connectionist, it also deals with hybrid systems, and will be of interest to both theoreticians as well as computer modellers. Range of topics covered: Connectionism and Cognitive Linguistics Motion, Chomsky's Government-binding Theory Syntactic Transformations on Distributed Representations Syntactic Neural Networks A Hybrid Symbolic/Connectionist Model for Understanding of Nouns Connectionism and Determinism in a Syntactic Parser Context Free Grammar Recognition Script Recognition with Hierarchical Feature Maps Attention Mechanisms in Language Script-Based Story Processing A Connectionist Account of Similarity in Vowel Harmony Learning Distributed Representations Connectionist Language Users Representation and Recognition of Temporal Patterns A Hybrid Model of Script Generation Networks that Learn about Phonological Features Pronunciation in Text-to-Speech Systems

Here are the comprehensive details on cutting edge technologies employing neural networks for speech recognition and speech processing in modern communications. Going far beyond the simple speech recognition technologies on the market today, this new book, written by and for speech and signal processing engineers in industry, R&D, and academia, takes you to the forefront of the hottest emergent neural net-based speech processing techniques.

This book collects together refereed versions of papers presented at the Eighth Neural Computation and Psychology Workshop (NCPW 8). NCPW is a well-established workshop series that brings together researchers from different disciplines, such as artificial intelligence, cognitive science, computer science, neurobiology, philosophy and psychology. The articles are centred on the theme of connectionist modelling of cognition and perceptionn. The proceedings have been selected for coverage in: • Index to Scientific & Technical Proceedings® (ISTP® / ISI Proceedings) • Index to Scientific & Technical Proceedings (ISTP CDROM version / ISI Proceedings) • Index to Social Sciences & Humanities Proceedings® (ISSHP® / ISI Proceedings) • Index to Social Sciences & Humanities Proceedings (ISSHP CDROM version / ISI Proceedings) • CC Proceedings — Engineering & Physical Sciences • CC Proceedings — Biomedical, Biological & Agricultural Sciences Contents:An Extended Buffer Model for Active Maintenance and Selective Updating (E J Davelaar & M Usher)Applying Forward Models to Sequence Learning: A Connectionist Implementation (D Theofilou, A Destrebecqz & A Cleeremans)Modelling Asymmetric Infant Categorization with the Representational Acuity Hypothesis (G Westermann & D Mareschal)Solving the Visual Expertise Mystery (C A Joyce & G W Cottrell)Through Attention to Consciousness by CODAM (J G Taylor)Modeling Visual Search: Evolving the Selective Attention for Identification Model (SAIM) (D Heinke, G W Humphreys & C L Tweed)A Temporal Attractor Framework for the Development of Analogical Completion (R Leech, D Mareschal & R Cooper)On the Evolution of Irrational Behaviour (J A Bullinaria)Reading, Sublexical Units and Scrambled Words: Capturing the Human Data (R C Shillcock & P Monaghan)and other papers Readership: Graduate students, academics and researchers in neural networks, artificial intelligence and psychology. Keywords:Neural Networks;Connectionism;Psychology;Perception;Cognition

An evaluation of the merits, potential, and limits of Connectionism, this book also illustrates current research programs and recent trends.Connectionism (also known as Neural Networks) is an exciting new field which has brought together researchers from different areas such as artificial intelligence, computer science, cognitive science, neuroscience, physics, and complex dynamics. These researchers are applying the connectionist paradigm in an interdisciplinary way to the analysis and design of intelligent systems.In this book, researchers from the above-mentioned fields not only report on their most recent research results, but also describe Connectionism from the perspective of their own field, looking at issues such as: - the effects and the utility of Connectionism for their field - the potential and limitations of Connectionism - can it be combined with other approaches?