This volume contains invited and contributed papers presented at the NATO Advanced study Insti tute on "Recent Advances in Speech Understanding and Dialog systems" held in Bad Windsheim, Federal Republic of Germany, July 5 to July 18, 1987. It is divided into the three parts Speech coding and Segmentation, Word Recognition, and Linguistic Processing. Although this can only be a rough organization showing some overlap, the editors felt that it most naturally represents the bottom-up strategy of speech understanding and, therefore, should be useful for the reader. Part 1, SPEECH CODING AND SEGMENTATION, contains 4 invited and 14 contributed papers. The first invited paper summarizes basic properties of speech signals, reviews coding schemes, and describes a particular solution which guarantees high speech quality at low data rates. The second and third invited papers are concerned with acoustic-phonetic decoding. Techniques to integrate knowledge­ sources into speech recognition systems are presented and demonstrated by experimental systems. The fourth invited paper gives an overview of approaches for using prosodic knowledge in automatic speech recogni tion systems, and a method for assigning a stress score to every syllable in an utterance of German speech is reported in a contributed paper. A set of contributed papers treats the problem of automatic segmentation, and several authors successfully apply knowledge-based methods for interpreting speech signals and spectrograms. The last three papers investigate phonetic models, Markov models and fuzzy quantization techniques and provide a transi tion to Part 2 .

Inhalt

1: Speech Coding and Segmentation.- Invited Papers.- Recent Advances in Speech Coding.- Acoustic-Phonetic Decoding of Speech.- Knowledge-Based Approaches in Acoustic-Phonetic Decoding of Speech.- The Use of Prosodic Parameters in Automatic Speech Recognition.- Contributed Papers.- Prosodie Features in German Speech: Stress Assignment by Man and Machine.- Recognition of Speech Using Temporal Decomposition.- LongTerm Analysis-Synthesis of Speech by Non- Stationary AR Methods.- Using Contextual Information in View of Formant Speech Analysis Improvement.- A Speech Recognition Strategy Based on Making Acoustic Evidence and Phonetic Knowledge Explicit.- On Finding Objects in Spectrograms: A Multiscale Relaxation Labelling Approach.- Phonetic Segmentation Using Psychoacoustic Speech Parameters.- Morphological Representation of Speech Knowledge for Automatic Speech Recognition Systems.- Speaker-Independent Automatic Recognition of Plosive Sound in Letters and Digits.- A Real-Time Auditory Model: Description and Applications in an ASR Acoustic-Phonetic Front End.- A New Phonematic Approach to Speech Recognition.- Primary Perceptual Units in Word Recognition.- Context-Dependent Phone Markov Models for Speech Recognition.- Speech Recognition Based on Speech Units.- 2: Word Recognition.- Invited Papers.- Mathematical Foundations of Hidden Markov Models.- Computer Recognition of Spoken Letters and Digits.- Recognition of Words in Very Large Vocabulary.- Contributed Papers.- Isolated Word Recognition Using Hidden Markov Models.- Isolated Digit Recognition Using the Multi-Layer Perceptron.- Use of Procedural Knowledge for Spoken Letters and Digits Recognition.- Real-Time Large Vocabulary Word Recognition via Diphone Spotting and Multiprocessor Implementation.- Speech Recognition With Difficult Dictionaries.- Recent Results on the Application of a Metric-Space Search Algorithm (AESA) to Multispeaker Data.- Robust Features for Word Recognition.- Statistical Analysis of Left-to-Right Parser for Word-Hypothesing.- Overview of Speech Recognition in the 'SPICOS' System.- An Experimental Environment for Generating Word Hypotheses in Continuous Speech.- Application of the Error Correcting Grammatical Inference Method (ECGI)to Multi-Speaker Isolated Word Recognition.- Multi-Speaker Experiments With the Morphic Generator Grammatical Inference Methodology.- A New Approach to Template Selection for Speaker Independent Word Recognition.- Dynamic Spectral Adaptation of Automatic Speech Recognizers to New Speakers.- Towards Speaker-Independent Continuous Speech Recognition.- Evaluating Speech Recognizers and Data Bases.- 3:Linguistic Processing.- Invited Papers.- On-Line Interpretation in Speech Understanding and Dialogue Systems.- Semantic Processing in Speech Understanding.- Knowledge Based Systems for Speech Understanding.- Contributed Papers.- Recognition of Speaker-Dependent Continuous Speech with KEAL-NEVEZH.- Modification of Earley's Algorithm for Speech Recognition.- Expectation-Based Speech Recognition.- Merging Acoustics and Linguistics in Speech Understanding.- Using Semantic and Pragmatic Knowledge for the Interpretation of Syntactic Constituents.- Tksk-Oriented Dialogue Processing in Human-Computer Voice Communication.- Experimentation in the Specification of an Oral Dialogue.- List of Participants.- Author Index.