You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

111 lines
1.5 KiB

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

Contents
II Synthesis
7 Survey of speech synthesis technology
7.1 Overview
7.2 Background
7.3 Synthesis techniques
7.4 Applications
8 The phonological component
8.1 Overview
8.2 Input representation for a sentence
8.3 Comparison between ideal synthesis input and system performance
8.4 Stress rules
8.5 Rules of segmental phonology
8.6 Pauses
8.7 Evaluation of the analysis modules
9 The prosodic component
9.1 Overview
9.2 Segmental durations
10 The fundamental frequency generator
10.1 Overview
10.2 Input
10.3 OQutput
10.4 The OShaughnessy fundamental frequency algorithm
10.5 Adjustments to the OShaughnessy algorithm
10.6 Potential improvements from additional syntactic information
11 The phonetic component
11.1 Overview
11.2 “Synthesis-by-analysis” of consonant-vowel syllables
11.3 General rules for the synthesis of phonetic sequences
11.4 Summary
12 The Klatt formant synthesizer
12.1 Overview
12.2 Vocal tract transfer functions
12.3 Radiation characteristic
13 Some measures of intelligibility and comprehension
13.1 Overview
13.2 Phoneme recognition
13.3 Word recognition in sentences
13.4 Comprehension
13.5 General discussion and conclusions
14 Implementation
14.1 Conceptual organization
14.2 Development system
14.3 Performance system
14.4 UNIX implementation
14.5 Using the system
vi
71
71
72
73
79
81
81
81
85
86
87
88
89
93
93
93
100
100
101
102
103
107
107
108
108
109
116
122
123
123
139
150
151
151
152
157
161
167
172
172
173
174
174
175