ILLUSTRATIONS |
| Figures |
| 1 |
Steps in converting text to speech |
| 2 |
Block diagram of sentence generation process |
| 3 |
Successive stages of transformation of "Joe ate his soup" |
| 4 |
Chart of historical development of text-to-speech systems |
| 5 |
The Voder speech synthesizer (1939) |
| 6 |
The Haskins Pattern Playback (1951) |
| 7 |
The OVE-II speech synthesizer (1962) |
| 8 |
The Holmes parallel formant synthesizer (1973) |
| 9 |
Spectrograms of natural utterance and synthetic imitation (1973) |
| 10 |
Comparison of voicing waveforms |
| 11 |
Selected spectra of Klattalk voicing source |
| 12 |
Block diagram of Klattalk synthesizer (1980) |
| 13 |
Magnitude spectrum of aspiration noise |
| 14 |
The DAVO articulatory synthesizer (1958) |
| 15 |
Spectrograms identifying the "hub" of /b/ (1947) |
| 16 |
Illustration of the locus theory (1955) |
| 17 |
Pattern Playback patterns for plosives and nasals |
| 18 |
Spectrograms of English vowel-consonant-vowels |
| 19 |
Locus theory specification of formant motions (1964) |
| 20 |
Plot of measured onset frequencies of formant transitions (1979) |
| 21 |
Linear prediction spectra of plosive bursts (1979) |
| 22 |
Articulation-based vocal tract synthesizer (1976) |
| 23 |
Spectrograms of diphone juxtaposition |
| 24 |
Spectrograms of concatenated words vs words in sentence |
| 25 |
Example fundamental frequency "hat pattern" |
| 26 |
Klattalk fo contour for a sentence |
| 27 |
Spectrograms of allophonic variations of /t/ |
| 28 |
Model of formant transitions for [bId] |
| 29 |
Formant transitions for vowel-/g/-vowels |
| 30 |
Flowchart of text analysis |
| 31 |
History of text-to-phoneme algorithms |
| 32 |
Frequency analysis of million-word corpus |
| 33 |
Electronic hardware for DECtalk (1983) |
| 34 |
Critical-band spectra of vowel-pairs |
| |
| Tables |
| 1 |
Physical and subjective components of sentence prosody |
| 2 |
Duration rules proposed by Klatt (1979a) |
| 3 |
Two-character representations for selected allophones in Klattalk |
| 4 |
Representations for phonemes in DECtalk |
| 5 |
Representations for stress and syntactic symbols in DECtalk |
| 6 |
Techniques for evaluating text-to-speech systems |
| 7 |
Performance tests using the modified rhyme test |
| 8 |
Consonant intelligibility in nonsense syllables, LPC encoding |
| 9 |
Word intelligibility of text-to-speech systems |
| 10 |
Word intelligibility of inexpensive text-to-speech systems |
| 11 |
Listening comprehension performance of text-to-speech systems |
| 12 |
Commercial applications for text-to-speech |
| 13 |
Research issues for improving text-to-speech systems |
| |