Speech Recognition and Coding: New Advances and Trends

✍ Scribed by Jean-Paul Haton (auth.), Antonio J. Rubio Ayuso, Juan M. López Soler (eds.)

• Publisher: Springer-Verlag Berlin Heidelberg
• Year: 1995
• Tongue: English
• Leaves: 516
• Series: NATO ASI Series 147
• Edition: 1
• Category: Library

✦ Synopsis

Based on a NATO Advanced Study Institute held in 1993, this book addresses recent advances in automatic speech recognition and speech coding. The book contains contributions by many of the most outstanding researchers from the best laboratories worldwide in the field. The contributions have been grouped into five parts: on acoustic modeling; language modeling; speech processing, analysis and synthesis; speech coding; and vector quantization and neural nets. For each of these topics, some of the best-known researchers were invited to give a lecture. In addition to these lectures, the topics were complemented with discussions and presentations of the work of those attending. Altogether, the reader is given a wide perspective on recent advances in the field and will be able to see the trends for future work.

✦ Table of Contents

Front Matter....Pages i-xi
Front Matter....Pages 1-1
Automatic Recognition of Noisy Speech....Pages 3-13
Adaptive Learning in Acoustic and Language Modeling....Pages 14-31
Evaluation of ASR Systems, Algorithms and Databases....Pages 32-40
Statistical and Discriminative Methods for Speech Recognition....Pages 41-55
Automatic Speech Labeling Using Word Pronunciation Networks and Hidden Markov Models....Pages 56-59
Heuristic Search Methods for a Segment Based Continuous Speech Recognizer....Pages 60-63
Dimension and Structure of the Vowel Space....Pages 64-67
Continuous Speech HMM Training System: Applications to Speech Recognition and Phonetic Label Alignment....Pages 68-71
HMM Based Acoustic-Phonetic Decoding with Constrained Transitions and Speaker Topology....Pages 72-75
Experiments on a Fast Mixture Density Likelihood Computation....Pages 76-79
Explicit Modelling of Duration in HMM: an Efficient Algorithm....Pages 80-83
Acoustic-Phonetic Decoding of Spanish Continuous Speech with Hidden Markov Models....Pages 84-87
HMM-Based Speech Recognition in Noisy Car Environment....Pages 88-91
Extensions to the AESA for Finding k -Nearest-Neighbours....Pages 92-95
An Efficient Pruning Algorithm for Continuous Speech Recognition....Pages 96-99
On the Performance of SCHMM for Isolated Word Recognition and Rejection....Pages 100-103
A Speaker Independent Isolated Word Recognition System for Turkish....Pages 104-107
The Speech Recognition Research System of the TU Dresden....Pages 108-111
A MMI Codebook Design for MVQHMM Speech Recognition....Pages 112-115
SLHMM: An ANN Approach for Continuous Speech Recognition....Pages 116-119
Front Matter....Pages 1-1
Medium Vocabulary Audiovisual Speech Recognition....Pages 120-123
SLAM: A PC-Based Multi-Level Segmentation Tool....Pages 124-127
Durational Modelling in HMM-based Speech Recognition: Towards a Justified Measure....Pages 128-131
Rejection in Speech Recognition for Telecommunication Applications....Pages 132-135
Front Matter....Pages 137-137
A Learning Approach to Natural Language Understanding....Pages 139-156
Language Models for Automatic Speech Recognition....Pages 157-173
Grammatical Inference and Automatic Speech Recognition....Pages 174-191
Statistical Modeling of Segmental and Suprasegmental Information....Pages 192-209
Search Strategies For Large-Vocabulary Continuous-Speech Recognition....Pages 210-225
Two New Approaches to Language Modeling: A Tutorial....Pages 226-239
Representing Word Pronunciations as Trees....Pages 240-243
Language Models Comparison in a Robot Telecontrol Application....Pages 244-247
Keyword Propagation Viterbi Algorithm....Pages 248-251
Dialog and Language Modeling in CRIM’s ATIS System....Pages 252-255
On the Use of the Leaving-One-Out Method in Statistical Language Modelling....Pages 256-259
Application of Grammar Constraints to ASR Using Signature Functions....Pages 260-263
CRIM Hidden Markov Model Based Keyword Recognition System....Pages 264-267
Modelling Phone-Context in Spanish by Using SCMGGI Models....Pages 268-271
Efficient Integration of Context-Free Language Models in Continuous Speech Recognition....Pages 272-275
Keyword Spotting, an Application for Voice Dialing....Pages 276-279
Front Matter....Pages 281-281
Telecommunications Applications of Speech Processing....Pages 283-300
Disambiguating Hierarchical Segmentations of Speech Signals....Pages 301-304
Talker Tracking using two Microphone Pairs and a CrosspowerSpectrum Phase Analysis....Pages 305-308
A Text-to-Speech Services Architecture for UNIX....Pages 309-312
Comparison of Parametric Spectral Representations for Voice Recognition in Noisy Environments....Pages 313-316
Spectral Analysis of Turkish Vowels and a Comparison of Vowel Normalization Algorithms....Pages 317-320
Can You Tell Apart Spontaneous and Read Speech if You Just Look at Prosody?....Pages 321-324
The Prosodic Marking of Phrase Boundaries: Expectations and Results....Pages 325-328
Voice Source State as a Source of Information in Speech Recognition: Detection of Laryngealizations....Pages 329-332
Voice Transformations for the Evaluation of Speaker Verification Systems....Pages 333-336
Towards a More Realistic Evaluation of Synthetic Speech: A Cognitive Perspective....Pages 337-340
A Non-Linear Speech Analysis Based on Modulation Information....Pages 341-344
The Recognition Component of the SUNDIAL Project....Pages 345-348
Front Matter....Pages 349-349
An Overview of Different Trends on CELP Coding....Pages 351-368
Concepts and Paradigms in Speech Coding....Pages 369-386
Speech Coding over Noisy Channels†....Pages 387-404
Lattice and Trellis Coded Quantizations for efficient Coding of Speech....Pages 405-422
8 kbit/s LD-CELP Coding for Mobile Radio....Pages 423-426
Subband Long-Term Prediction for LPC-Coders....Pages 427-430
On the Use of Interframe Information of Line Spectral Frequencies in Speech Coding....Pages 431-434
Front Matter....Pages 349-349
Speech Coding Using the Karhunen-Lóeve Representation of the Spectral Envelope of Acoustic Subwords....Pages 435-438
Excitation Construction for the Robust Low Bit Rate CELP Speech Coder....Pages 439-442
A Discrete Cosine Transform Scheme for Low-Delay Wideband Speech Coding....Pages 443-446
MOR-VQ for Speech Coding Over Noisy Analog Channels....Pages 447-450
Improved CELP Coding Using a Fully Adaptive Excitation Codebook....Pages 451-454
Front Matter....Pages 455-455
Recent Advances in JANUS: A Speech Translation System....Pages 457-472
On a Fuzzy DVQ Algorithm for Speech Recognition....Pages 473-476
On the Use of Recurrent Neural Networks for Grammar Learning and Word Spotting....Pages 477-480
LVQ-based Codebooks in Phonemic Speech Recognition....Pages 481-484
Distributed and Local Neural Classifiers for Phoneme Recognition†....Pages 485-488
A VQ Algorithm Based on Genetic Algorithms and LVQ....Pages 489-492
Vector Quantization Based Classification and Maximum Likelihood Decoding for Speaker Recognition†....Pages 493-495
Evidence Combination in Speech Recognition Using Neural Networks....Pages 497-500
Back Matter....Pages 501-514

✦ Subjects

Signal, Image and Speech Processing;Artificial Intelligence (incl. Robotics);Pattern Recognition;Simulation and Modeling;Language Translation and Linguistics;Acoustics