Learning is a key issue in the analysis and design of all kinds of intelligent systems. In recent time many new paradigms of automated (machine) learning have been proposed in the literature. Soft computing, that has proved to be an effective and efficient tool in so many areas of science and technology, seems to offer new qualities in the realm of machine learning too. The purpose of this volume is to present some new learning paradigms that have been triggered, or at least strongly influenced by soft computing tools and techniques, mainly related to neural networks, fuzzy logic, rough sets, and evolutionary computations.

Speech Recognition: Invited Papers Presented at the 1974 IEEE Symposium discusses several topics, including speech recognition systems, systems organization, acoustic-phonetics, parameter extraction, as well as syntax and semantics. Organized into five parts encompassing 20 chapters, this compilation of papers starts with an overview of the basic structure of speech understanding systems. This text then discusses the practical applications of automatic speech recognition in several areas, including quality control inspection, automated material handling, direct communication with computers, and inventory taking and control. Other chapters consider the operational methods for applying higher level of information to decode the acoustic ambiguities encountered when recognizing larger vocabularies and continuous speech. The final chapter deals with stochastic modeling, which is a valuable and versatile procedure for automatic speech analysis. This book is a valuable resource for scientists and researchers in the fields of artificial intelligence, acoustic-phonetics, linguistics, and computer architecture.