The book collects the contributions to the NATO Advanced Study Institute on "Speech Recognition and Understanding: Recent Advances, Trends and Applications", held in Cetraro, Italy, during the first two weeks of July 1990. This Institute focused on three topics that are considered of particular interest and rich of i'p.novation by researchers in the fields of speech recognition and understanding: Advances in Hidden Markov modeling, connectionist approaches to speech and language modeling, and linguistic processing including language and dialogue modeling. The purpose of any ASI is that of encouraging scientific communications between researchers of NATO countries through advanced tutorials and presentations: excellent tutorials were offered by invited speakers that present in this book 15 papers which sum­ marize or detail the topics covered in their lectures. The lectures were complemented by discussions, panel sections and by the presentation of related works carried on by some of the attending researchers: these presentations have been collected in 42 short contributions to the Proceedings. This volume, that the reader can find useful for an overview, although incomplete, of the state of the art in speech understanding, is divided into 6 Parts.

Table of Contents:
1 Recent Results on Hidden Markov Models.- Invited papers.- Hidden Markov Models for Speech Recognition — Strengths and Limitations.- Hidden Markov Models and Speaker Adaptation.- A 20,000 word Automatic Speech Recognizer. Adaptation to French of the US TANGORA System.- Automatic Adjustments of the Markov Models Topology for Speech Recognition Applications over the Telephone.- Phonetic Structure Inference of Phonemic HMM.- Phonetic Units and Phonotactical Structure Inference by Ergodic Hidden Markov Models.- Clustering of Gaussian Densities in Hidden Markov Models.- Developments in High-Performance Connected Digit Recognition.- Robust Speaker-Independent Hidden Markov Model Based Word Spotter.- Robust Speech Recognition in Noisy and Reverberant Environments.- An ISDN Speech Server based on Speaker Independent Continuous Hidden Markov Models.- RAMSES: A Spanish Demisyllable Based Continuous Speech Recognition System.- Speaker Independent, 1000 Words Speech Recognition in Spanish.- Continuously Variable Transition Probability HMM for Speech Recognition.- 2 Continuous Speech Recognition Systems.- Invited papers.- Context-Dependent Phonetic Hidden Markov Models for Speaker-Independent Continuous Speech Recognition (Abstract).- Speaker-Independent Continuous Speech Recognition Using Continuous Density Hidden Markov Models.- Contributed papers.- A Fast Lexical Selection Strategy for Large Vocabulary Continuous Speech Recognition.- Performance of a Speaker-Independent Continuous Speech Recognizer.- Automatic Transformation of Speech Databases for Continuous Speech Recognition.- Iterative Optimization of the Data Driven Analysis in Continuous Speech.- Syllable-based Stochastic Models for Continuous Speech Recognition.- Word Hypothesization in Continuous Speech Recognition.-Phone Recognition Using High Order Phonotactic Constraints.- An Efficient Structure for Continuous Speech Recognition.- Search Organization for Large Vocabulary Continuous Speech Recognition.- 3 Connectionist Models of Speech.- Invited papers.- Neural Networks or Hidden Markov Models for Automatic Speech Recognition: Is there a Choice?.- Neural Networks for Continuous Speech Recognition.- Connectionist Large Vocabulary Speech Recognition.- The Cortical Column as a Model for Speech Recognition: Principles and First Experiments.- Contributed papers.- Radial Basis Functions for Speech Recognition.- Phonetic Features Extraction Using Time-Delay Neural Networks.- Improved Broad Phonetic Classification and Segmentation with an Auditory Model.- Automatic Learning of a Production Rule System for Acoustic-Phonetic Decoding.- 4 Stochastic Models for Language and Dialogue.- Invited papers.- Stochastic Grammars and Pattern Recognition.- Basic Methods of Probabilistic Context Free Grammars.- A Probabilistic Approach to Person-Robot Dialogue.- Contributed papers.- Experimenting Text Creation by Natural-Language, Large-Vocabulary Speech Recognition.- DUALGRAM: An Efficient Method for Representing Limited-Domain Language Models.- Strategies for Speech Recognition and Understanding Using Layered Protocols.- 5 Understanding and Dialogue Systems.- Invited papers.- TINA: A Probabilistic Syntactic Parser for Speech Understanding Systems.- The Voyager Speech Understanding System: A Progress Report.- The Interaction of Word Recognition and Linguistic Processing in Speech Understanding.- Linguistic Processing in a Speech Understanding System.- Contributed papers.- Linguistic Tools for Speech Recognition and Understanding.- Evidential Reasoning and the Combination of Knowledge and StatisticalTechniques in Syllable Based Speech Recognition.- 6 Speech Analysis, Coding and Segmentation.- Contributed papers.- Data Base Management for Use with Acoustic-Phonetic Speech Data Bases.- BPF Outputs Compared with Formant Frequencies and LPCs for the Recognition of Vowels.- A Codification of Error Signal by Splines Functions.- Specific Distance for Feature Selection in Speech Recognition.- Multiple Template Modeling of Sublexical Units.- Learning Structural Models of Sublexical Units.- On the Use of Negative Samples in the MGGI Methodology and its Application for Difficult Vocabulary Recognition Tasks.- A New Method for Dynamic Time Alignment of Speech Waveforms.- A New Technique for Automatic Segmentation of Continuous Speech.- Segmentation of Speech based upon a Linear Model of the Effects of Coarticulation 549 P.J. D.