Klatt, Review of text-to-speech conversion for English

Home | Demos | Research | Download

Audio recordings from the Appendix of D. Klatt, "Review of text-to-speech conversion for English," J. of the Acoustical Society of America, 82(3) September 1987.

Introduction

Part A: Development of speech synthesizers

Example 1 The VODER of Homer Dudley, 1939.
Example 2 The Pattern Playback designed by Franklin Cooper, 1951.
Example 3 PAT, the "Parametric Articficial Talker" of Walter Lawrence, 1953.
Example 4 The "OVE" cascade formant synthesizer of Gunnar Fant
Example 5 Copying a natural sentence using Walter Lawerence's PAT formant synthesizer, 1962.
Example 6 Copying the same sentence using the second generation of Gunar Fant's OVE cascade formant synthesizer, 1962.
Example 7 Comparison of synthesis and a natural sentence, using OVE II, by John Holmes, 1961
Example 8 Comparison of synthesis and a natural sentence, John Holmes using his parallel formant synthesizer, 1973.
Example 9 Attempting to scale the DECtalk male voice to make it sound female.
Example 10 Comparison of synthesis and a natural sentence, fremale voice, Dennis Klatt, 1986b,
Example 11 The DAVO articulatory synthesizer developed by George Rosen at M.I.T., 1958.
Example 12 Sentences produced by an articulatory model, James Flanagan and Kenzo Ishizaka, 1976
Example 13 Linear-prediction analysis and resynthesis of speech at a low-bit rate in the Texas Instruments Speek'n'Spell toy, Richard Wiggins, 1980.
Example 14 Comparison of synthesis and a natural recording, automatic analysis-resynthesis using multipults linear prediction, Bishnu Atal, 1982.

Part B: Segmental synthesis by rule

Example 15 Creation of a sentence from rules in the head of Pierre Delattre, using the Haskins Pattern Playback, 1959.
Example 16 Output from the first computer-based phonemic-synthesis-by-rule program, created by John Kelly and Louis Gerstman, 1961.
Example 17 Elegant rule program for British English by John Holmes, Ignatius Mattingly, and John Shearme, 1964.
Example 18 Formant synthesis using diphone concatenation, by Rex Dixon and David Maxey, 1968.
Example 19 Rules to control a low-dimensionality articulatory model, by Cecil Coker, 1968.

Part C: Synthesis by rule of segments and sentence prosody

Example 20 First prosodic synthesis by rule, by Ignatius Mattingly, 1968.
Example 21 Sentence-level phonology incorporated in rules by Dennis Klatt, 1976.
Example 22 Concatenation of linear-prediction diphones, by Joe Olive, 1977.
Example 23 Concatenation of linear-prediction demisylables by Catherine Browman, 1980.

Part D: Fully Automatic text-to-speech conversion

Example 24 The first full text-to-speech system, done in Japan by Noriko Umeda et al., 1968.
Example 25 The first Bell Laboraatories text-to-speech system by Cecil Coker, Noriko Umeda, and Catherine Browman, 1973.
Example 26 The Haskins Laboratories text-to-speech system, 1973.
Example 27 The Kurzweil reading machine for the blind, Raymond Kurzweil, 1976.
Example 28 The inexpensive Votrax Type-n-Talk system, by Richard Gagnon, 1978.
Example 29 The Echo low-cost diphone concatenation system, about 1982.
Example 30 The M.I.T. MITalk system by Jonathan Allen, Sheri Hunnicut, and Dennis Klatt, 1979.
Example 31 The multi-language Infovox system, by Rolf Carlson, Bjorn Granstrom, and Sheri Hunnicut, 1982.
Example 32 The Speech Plus Inc. "Prose-2000" commercial system, 1982.
Example 33 The Klattalk system by Dennis Klatt of M.I.T. which formed the basis for Digital Equiptment Corporation's DECtalk commercial systenm 1983.
Example 34 The AT&T Bell Laboratories text-to-speech system, 1985.
Example 35 Several of the DECtalk voices.
Example 36 DECtalk speaking at about 300 words/minute.

Conclusion

Whole recording (zipped)

Thanks to Nelson Morgan, Jeff Gilbert, and Eric Fosler of ICSI-Berkeley for these samples.(morgan@icsi.berkeley.edu)