| Automatic Recognition of Noisy Speech | p. 3 |
| Adaptive Learning in Acoustic and Language Modeling | p. 14 |
| Evaluation of ASR Systems, Algorithms and Databases | p. 32 |
| Statistical and Discriminative Methods for Speech Recognition | p. 41 |
| Automatic Speech Labeling Using Word Pronunciation Networks and Hidden Markov Models | p. 56 |
| Heuristic Search Methods for a Segment Based Continuous Speech Recognizer | p. 60 |
| Dimension and Structure of the Vowel Space | p. 64 |
| Continuous Speech HMM Training System: Applications to Speech Recognition and Phonetic Label Alignment | p. 68 |
| HMM Based Acoustic-Phonetic Decoding with Constrained Transitions and Speaker Topology | p. 72 |
| Experiments on a Fast Mixture Density Likelihood Computation | p. 76 |
| Explicit Modelling of Duration in HMM: an Efficient Algorithm | p. 80 |
| Acoustic-Phonetic Decoding of Spanish Continuous Speech with Hidden Markov Models | p. 84 |
| HMM-Based Speech Recognition in Noisy Car Environment | p. 88 |
| Extensions to the AESA for Finding k-Nearest-Neighbours | p. 92 |
| An Efficient Pruning Algorithm for Continuous Speech Recognition | p. 96 |
| On the Performance of SCHMM for Isolated Word Recognition and Rejection | p. 100 |
| A Speaker Independent Isolated Word Recognition System for Turkish | p. 104 |
| The Speech Recognition Research System of the TU Dresden | p. 108 |
| A MMI Codebook Design for MVQHMM Speech Recognition | p. 112 |
| SLHMM: An ANN Approach for Continuous Speech Recognition | p. 116 |
| Medium Vocabulary Audiovisual Speech Recognition | p. 120 |
| SLAM: A PC-Based Multi-Level Segmentation Tool | p. 124 |
| Durational Modelling in HMM-based Speech Recognition: Towards a Justified Measure | p. 128 |
| Rejection in Speech Recognition for Telecommunication Applications | p. 132 |
| A Learning Approach to Natural Language Understanding | p. 139 |
| Language Models for Automatic Speech Recognition | p. 157 |
| Grammatical Inference and Automatic Speech Recognition | p. 174 |
| Statistical Modeling of Segmental and Suprasegmental Information | p. 192 |
| Search Strategies For Large-Vocabulary Continuous-Speech Recognition | p. 210 |
| Two New Approaches to Language Modeling: A Tutorial | p. 226 |
| Representing Word Pronunciations as Trees | p. 240 |
| Language Models Comparison in a Robot Telecontrol Application | p. 244 |
| Keyword Propagation Viterbi Algorithm | p. 248 |
| Dialog and Language Modeling in CRIM's ATIS System | p. 252 |
| On the Use of the Leaving-One-Out Method in Statistical Language Modelling | p. 256 |
| Application of Grammar Constraints to ASR Using Signature Functions | p. 260 |
| CRIM Hidden Markov Model Based Keyword Recognition System | p. 264 |
| Modelling Phone-Context in Spanish by Using SCMGGI Models | p. 268 |
| Efficient Integration of Context-Free Language Models in Continuous Speech Recognition | p. 272 |
| Keyword Spotting, an Application for Voice Dialing | p. 276 |
| Telecommunications Applications of Speech Processing | p. 283 |
| Disambiguating Hierarchical Segmentations of Speech Signals | p. 301 |
| Talker Tracking using two Microphone Pairs and a CrosspowerSpectrum Phase Analysis | p. 305 |
| A Text-to-Speech Services Architecture for UNIX | p. 309 |
| Comparison of Parametric Spectral Representations for Voice Recognition in Noisy Environments | p. 313 |
| Spectral Analysis of Turkish Vowels and a Comparison of Vowel Normalization Algorithms | p. 317 |
| Can You Tell Apart Spontaneous and Read Speech if You Just Look at Prosody? | p. 321 |
| The Prosodic Marking of Phrase Boundaries: Expectations and Results | p. 325 |
| Voice Source State as a Source of Information in Speech Recognition: Detection of Laryngealizations | p. 329 |
| Voice Transformations for the Evaluation of Speaker Verification Systems | p. 333 |
| Towards a More Realistic Evaluation of Synthetic Speech: A Cognitive Perspective | p. 337 |
| A Non-Linear Speech Analysis Based on Modulation Information | p. 341 |
| The Recognition Component of the SUNDIAL Project | p. 345 |
| An Overview of Different Trends on CELP Coding | p. 351 |
| Concepts and Paradigms in Speech Coding | p. 369 |
| Speech Coding over Noisy Channels | p. 387 |
| Lattice and Trellis Coded Quantizations for Efficient Coding of Speech | p. 405 |
| 8 kbit/s LD-CELP Coding for Mobile Radio | p. 423 |
| Subband Long-Term Prediction for LPC-Coders | p. 427 |
| On the Use of Interframe Information of Line Spectral Frequencies in Speech Coding | p. 431 |
| Speech Coding Using the Karhunen-Loeve Representation of the Spectral Envelope of Acoustic Subwords | p. 435 |
| Excitation Construction for the Robust Low Bit Rate CELP Speech Coder | p. 439 |
| A Discrete Cosine Transform Scheme for Low-Delay Wideband Speech Coding | p. 443 |
| MOR-VQ for Speech Coding Over Noisy Analog Channels | p. 447 |
| Improved CELP Coding Using a Fully Adaptive Excitation Codebook | p. 451 |
| Recent Advances in JANUS: A Speech Translation System | p. 457 |
| On a Fuzzy DVQ Algorithm for Speech Recognition | p. 473 |
| On the Use of Recurrent Neural Networks for Grammar Learning and Word Spotting | p. 477 |
| LVQ-based Codebooks in Phonemic Speech Recognition | p. 481 |
| Distributed and Local Neural Classifiers for Phoneme Recognition | p. 485 |
| A VQ Algorithm Based on Genetic Algorithms and LVQ | p. 489 |
| Vector Quantization Based Classification and Maximum Likelihood Decoding for Speaker Recognition | p. 493 |
| Evidence Combination in Speech Recognition Using Neural Networks | p. 497 |
| Author Index | p. 501 |
| Subject Index | p. 503 |
| Table of Contents provided by Blackwell. All Rights Reserved. |
