Speech Recognition and Coding Book

1	Automatic Recognition of Noisy Speech	3
2	Adaptive Learning in Acoustic and Language Modeling	14
3	Evaluation of ASR Systems, Algorithms and Databases	32
4	Statistical and Discriminative Methods for Speech Recognition	41
5	Automatic Speech Labeling Using Word Pronunciation Networks and Hidden Markov Models	56
6	Heuristic Search Methods for a Segment Based Continuous Speech Recognizer	60
7	Dimension and Structure of the Vowel Space	64
8	Continuous Speech HMM Training System: Applications to Speech Recognition and Phonetic Label Alignment	68
9	HMM Based Acoustic-Phonetic Decoding with Constrained Transitions and Speaker Topology	72
10	Experiments on a Fast Mixture Density Likelihood Computation	76
11	Explicit Modelling of Duration in HMM: an Efficient Algorithm	80
12	Acoustic-Phonetic Decoding of Spanish Continuous Speech with Hidden Markov Models	84
13	HMM-Based Speech Recognition in Noisy Car Environment	88
14	Extensions to the AESA for Finding k-Nearest-Neighbours	92
15	An Efficient Pruning Algorithm for Continuous Speech Recognition	96
16	On the Performance of SCHMM for Isolated Word Recognition and Rejection	100
17	A Speaker Independent Isolated Word Recognition System for Turkish	104
18	The Speech Recognition Research System of the TU Dresden	108
19	A MMI Codebook Design for MVQHMM Speech Recognition	112
20	SLHMM: An ANN Approach for Continuous Speech Recognition	116
21	Medium Vocabulary Audiovisual Speech Recognition	120
22	SLAM: A PC-Based Multi-Level Segmentation Tool	124
23	Durational Modelling in HMM-based Speech Recognition: Towards a Justified Measure	128
24	Rejection in Speech Recognition for Telecommunication Applications	132
25	A Learning Approach to Natural Language Understanding	139
26	Language Models for Automatic Speech Recognition	157
27	Grammatical Inference and Automatic Speech Recognition	174
28	Statistical Modeling of Segmental and Suprasegmental Information	192
29	Search Strategies For Large-Vocabulary Continuous-Speech Recognition	210
30	Two New Approaches to Language Modeling: A Tutorial	226
31	Representing Word Pronunciations as Trees	240
32	Language Models Comparison in a Robot Telecontrol Application	244
33	Keyword Propagation Viterbi Algorithm	248
34	Dialog and Language Modeling in CRIM's ATIS System	252
35	On the Use of the Leaving-One-Out Method in Statistical Language Modelling	256
36	Application of Grammar Constraints to ASR Using Signature Functions	260
37	CRIM Hidden Markov Model Based Keyword Recognition System	264
38	Modelling Phone-Context in Spanish by Using SCMGGI Models	268
39	Efficient Integration of Context-Free Language Models in Continuous Speech Recognition	272
40	Keyword Spotting, an Application for Voice Dialing	276
41	Telecommunications Applications of Speech Processing	283
42	Disambiguating Hierarchical Segmentations of Speech Signals	301
43	Talker Tracking using two Microphone Pairs and a CrosspowerSpectrum Phase Analysis	305
44	A Text-to-Speech Services Architecture for UNIX	309
45	Comparison of Parametric Spectral Representations for Voice Recognition in Noisy Environments	313
46	Spectral Analysis of Turkish Vowels and a Comparison of Vowel Normalization Algorithms	317
47	Can You Tell Apart Spontaneous and Read Speech if You Just Look at Prosody?	321
48	The Prosodic Marking of Phrase Boundaries: Expectations and Results	325
49	Voice Source State as a Source of Information in Speech Recognition: Detection of Laryngealizations	329
50	Voice Transformations for the Evaluation of Speaker Verification Systems	333
51	Towards a More Realistic Evaluation of Synthetic Speech: A Cognitive Perspective	337
52	A Non-Linear Speech Analysis Based on Modulation Information	341
53	The Recognition Component of the SUNDIAL Project	345
54	An Overview of Different Trends on CELP Coding	351
55	Concepts and Paradigms in Speech Coding	369
56	Speech Coding over Noisy Channels	387
57	Lattice and Trellis Coded Quantizations for Efficient Coding of Speech	405
58	8 kbit/s LD-CELP Coding for Mobile Radio	423
59	Subband Long-Term Prediction for LPC-Coders	427
60	On the Use of Interframe Information of Line Spectral Frequencies in Speech Coding	431
61	Speech Coding Using the Karhunen-Loeve Representation of the Spectral Envelope of Acoustic Subwords	435
62	Excitation Construction for the Robust Low Bit Rate CELP Speech Coder	439
63	A Discrete Cosine Transform Scheme for Low-Delay Wideband Speech Coding	443
64	MOR-VQ for Speech Coding Over Noisy Analog Channels	447
65	Improved CELP Coding Using a Fully Adaptive Excitation Codebook	451
66	Recent Advances in JANUS: A Speech Translation System	457
67	On a Fuzzy DVQ Algorithm for Speech Recognition	473
68	On the Use of Recurrent Neural Networks for Grammar Learning and Word Spot