Ainsworth / Ter Haar Mechanisms of Speech Recognition

International Series in Natural Philosophy
1. Auflage 2014
ISBN: 978-1-4831-3792-6
Verlag: Elsevier Science & Techn.
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 152 Seiten, Web PDF

Mechanisms of Speech Recognition explores the mechanisms underlying speech recognition. Topics covered include the auditory system, speech production, auditory psychophysics, speech synthesis and analysis, vowel and consonant recognition, and perception of prosodic features and of distorted speech. Automatic speech recognition and models of speech recognition are also given consideration. This volume consists of 11 chapters and begins with an overview of speech recognition, communication, and production. More specifically, it examines the way in which the organs of the vocal apparatus are employed to transform a message consisting of a string of linguistic units, such as words or phonemes, into a wave of continuous sounds which are recognized as speech. The auditory system and its parts are then described, from the ears to the organ of Corti and nerve cells. The chapters that follow focus on the behavior of the hearing system, the various techniques of analyzing speech sounds, and speech synthesizers such as vocoders. The mechanisms underlying the recognition of vowels and consonants are also described, along with the physical parameters of the speech wave which signal the prosody of an utterance, the effects of distortions in the speech wave on speech perception, and tools used in automatic speech recognition. The book concludes with an evaluation of models of speech recognition. This book will be of interest to phoneticians, linguists, physiologists, psychologists, and physicists.

Autoren/Hrsg.

Ainsworth, W. A.

Ter Haar, D.

Inhaltsverzeichnis

1;Front Cover;1
2;Mechanisms of Speech Recognition;4
3;Copyright Page;5
4;Table of Contents;6
5;Foreword;9
6;CHAPTER 1. SPEECH PRODUCTION;10
6.1;Introduction;10
6.2;Speech communication;11
6.3;Phonemes;11
6.4;Vocal apparatus;12
6.5;Production of vowels;14
6.6;Diphthongs;17
6.7;Nasals;18
6.8;Semivowels;18
6.9;Fricatives;19
6.10;Plosives;20
6.11;Affricates;20
6.12;Conclusions;20
7;CHAPTER 2. THE AUDITORY SYSTEM;21
7.1;Outer ear;21
7.2;Middle ear;22
7.3;Inner ear;22
7.4;Organ of Corti;24
7.5;Nerve cells;25
7.6;Pathways in the auditory system;25
7.7;Single unit recording;26
7.8;Frequency selectivity of the cochlea;27
7.9;Units of the lower auditory system;28
7.10;Lateral suppression;29
7.11;Multiple-peak stimuli;30
7.12;Units in the auditory cortex;30
8;CHAPTER 3. AUDITORY PSYCHOPHYSICS;32
8.1;Threshold of hearing;32
8.2;Intensity discrimination;33
8.3;Frequency thresholds;33
8.4;Frequency discrimination;34
8.5;Pitch;35
8.6;Loudness;36
8.7;Critical bands;36
8.8;Perception of duration;37
8.9;Fatigue;38
8.10;Masking;39
8.11;Pulsation thresholds;39
8.12;Theories of hearing;40
9;CHAPTER 4. SPEECH ANALYSIS;43
9.1;Speech waveforms;43
9.2;Spectrum analysis;45
9.3;Sound spectrograph;46
9.4;Vowel sounds;47
9.5;Diphthongs;51
9.6;Semivowels;52
9.7;Nasals;53
9.8;Fricatives;53
9.9;Stop consonants;54
9.10;Affricates;54
9.11;Co-articulation;60
9.12;Distinctive features;60
9.13;Contextual constraints;60
9.14;Statistics of spoken English;65
10;CHAPTER 5. SPEECH SYNTHESIS;68
10.1;Historical;68
10.2;Vocoders;68
10.3;Pattern playback;70
10.4;Formant synthesizers;70
10.5;Control of speech synthesizers;72
10.6;Digital synthesis;72
10.7;Linear predictive coding;73
10.8;Vocal tract synthesizers;74
10.9;Speech synthesis by rule;75
10.10;Transmission of speech signals;76
11;CHAPTER 6. VOWEL RECOGNITION;77
11.1;Dimensional analysis;77
11.2;Formant frequency estimation;78
11.3;Formant transitions;79
11.4;Vowel duration;80
11.5;Vocal tract normalization;81
11.6;Reliability of vowel perception;82
11.7;Difference limens for vowels;82
12;CHAPTER 7. CONSONANT RECOGNITION;84
12.1;Perception of semivowels;84
12.2;Perception of stop consonants;85
12.3;Perception of nasals;88
12.4;Perception of fricatives;88
12.5;Categorical perception;89
12.6;Consonant confusions;92
12.7;Adaptation;93
12.8;Hemispheric specialization;94
12.9;Bilateral adaptation;96
13;CHAPTER 8. PERCEPTION OF PROSODIC FEATURES;98
13.1;Perception of fundamental frequency;98
13.2;Perception of duration;98
13.3;Stress;99
13.4;Rhythm and tempo;100
13.5;Duration of syllables;101
13.6;Intonation;102
14;CHAPTER 9. PERCEPTION OF DISTORTED SPEECH;105
14.1;Frequency distortions;105
14.2;Amplitude distortions;106
14.3;Time distortions;107
14.4;Masking of speech;109
14.5;Effect of context;110
14.6;Cocktail-party effect;111
14.7;Verbal transformation effect;112
14.8;Perception of temporal order;112
15;CHAPTER 10. AUTOMATIC SPEECH RECOGNITION;113
15.1;Early speech recognizers;113
15.2;Other forms of pre-processing;115
15.3;Some problems;116
15.4;Analogue feature recognition system;117
15.5;Speaker-independent digit recognition;118
15.6;Continuous speech recognition;119
15.7;Sources of linguistic knowledge;119
15.8;Hierarchical systems;121
15.9;Top-down systems;123
15.10;Heterarchical systems;126
16;CHAPTER 11. MODELS OF SPEECH PERCEPTION;129
16.1;Short-term auditory memory;129
16.2;Location of speech detector mechanisms;129
16.3;Motor theory of speech perception;130
16.4;Auditory theory of speech perception;131
16.5;Models from automatic speech recognition;132
16.6;Conclusions;133
17;REFERENCES;134
18;AUTHOR INDEX;142
19;SUBJECT INDEX;146
20;OTHER TITLES IN THE SERIES IN NATURAL PHILOSOPHY;150