Klatt Audio Scribe Notes for EE225d


Note: these files are large (150-200 KB apiece), the whole thing is 6 MB. They are compressed with gzip.

Introduction

Part A: Development of speech synthesizers

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

Part B: Segmental synthesis by rule

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

Part C: Synthesis by rule of segments and sentence prosody

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

Part D: Fully Automatic text-to-speech conversion

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

Conclusion

Whole recording

Jeff Gilbert
gilbertj@eecs.berkeley.edu
Eric Fosler
fosler@icsi.berkeley.edu
$Date: 1997/01/15 18:08:22 $