SSSHP Contents | Labs | Abbr. | Index
 

TELESENSORY SYSTEMS, INC. (TSI)


1970-1982    455 N. Bernardo Ave
             Mountain View, CA 94043
             (415) 960-0920

1983-1988    SPEECH PLUS, INC.   (spin-off company for speech
             640 Clyde Court      products)
             P.O. Box 7461
             Mountain View, CA 94039-7461
             (415) 964-7023

1989-        SPEECH PLUS, INC.
             1293 Anvilwood Avenue
             P.O. Box 3703
             Sunnyvale, CA 94088-3703
             (408) 745-1818
 
 
CONTENTS:

HISTORY

OPTACON (1962-    )

REAL TIME TEXT TO SPEECH CONVERSION (1976-    )

BIOGRAPHIES


------------------------------------------------------------- Top
HISTORY


Telesensory Systems, Inc. was formed in 1970 by Stanford
University professors from the Electrical Engineering department.
The purpose of the company was to produce and sell high
technology aids for blind persons, that had been developed at the
University. A later product, the text to speech system PROSE
2000, required additional technology from the Massachusetts
Institute of Technology.  A history of this technology transfer
from MIT to Telesensory Systems, Inc. can be found in the
following reference:

1983 Goldhor, R.S. and R.T. Lund, "University-to-industry
     advanced technology transfer: a case study", Research Policy
     12, Center for Policy Alternatives, Massachusetts Institute
     of Technology, Cambridge, MA 02139, p. 69. (1983).  (K)
     By Richard Goldhor of Kurzweil Applied Intelligence and R.T.
     Lund of MIT.  (see SSSHP 60, 1981 draft and published paper.)



------------------------------------------------------------- Top
PROJECT: OPTACON (1962 -      )


A reading aid for the blind that converts the image of a printed
letter into a pattern of pin vibrations that can be read with one
finger. (Note: the Optacon, itself, is not a speech project, but
served as the input device for the later speech products).


1962 Original concept by John G. Linvill, Stanford University. 
     (The Institute, IEEE, Sept. 1983, p15).


1966 Funding from the U.S. Office of Education to establish the
     Integrated Circuits Laboratory at Stanford University to
     develop Optacon electronics.  $1.8 million over four years
     (The Institute, IEEE, Sept. 1983, p 15)


1969 Linvill, J.G., "Development progress on a microelectronic
     tactile facsimile reading aid for the blind," IEEE Trans on
     Audio and Electro., Vol. AU-17, No. 4, 271-274, Dec 1969.


1970 Formed Telesensory Systems, Inc. Dr. James Bliss, President,
     Dr. John G. Linvill, member board of directors.


1970 Commercial version of the Optacon (Model R1C).


1977 OPTACON - A READING SYSTEM FOR THE BLIND, product brochure,
     Telesensory Systems, Inc. (items SSSHP 19)

     ARTIFACT: for model of Optacon, contact Dr. J.C. Bliss,
               Telesensory System, Inc.


------------------------------------------------------------- Top
PROJECT: REAL TIME TEXT TO SPEECH CONVERSION (1976 -      )


"Development of commercial text-to-speech system, initially
intended for Optacon-based voice-output reading machine for the
blind.  Based upon 1976 version of Klatt synthesis-by-rule
software and MIT laboratory systems MITalk-77 and MITalk-79.
First resulting commercial product was PROSE 2000 Multibus board;
subsequent products were PROSE 2020 peripheral, CallText 5000 PC
board, CallText 5050 peripheral, CallText 5100 multichannel system
and CallText Voice Gateway System."  -  G. F. Groner, personal
communication to H.D. Maxey, 1988

PROSE units are for local use, over a speaker.  CallText units
have additional circuitry enabling them to work over telephone
lines.  Synthesis software is the same for both systems.


1977 Announcement of development project to produce portable
     text-to-speech device for use with Optacon. Synthesis from
     MIT system. Target date was late 1979, target price was
     $10,000. The Optacon's camera was manually moved across the
     page.


1977 Liniak, P.E., letter on TSI's Voice Communication Project,
     to H.D. Maxey, dated 1/22/79 (contains material from 1977)

     SSSHP 17 Tape: Telesensory Systems & Speech Plus TSI
          Speech/Reading System Announcement, 12/12/77.
          (human: "Computers are getting to sound more human every
          day.  ...  long synthetic discourse on project history
          ...  my human colleagues.")
          Cassette, good quality


1979 "Experimental Voice Reading System Demonstrated," TSI News-
     letter, Fall 1979. (don't have) Recording made from
     microphone at the first public demonstration, National
     Conference of the American Assoc. of Workers for the Blind,
     Oklahoma City, Oklahoma, July, 1979.  Some 6000 Opticons
     (without synthetic speech) currently in use.  System was
     competitive with Kurzweil Reading Machine (see SSSHP USA
     Kurzweil Computer Products file).  Product availability
     targeted for 1981.

     SSSHP 18.1 Tape: 1979 Introduction of Demonstration Voice
          Output Reading System, synthetic speech and interviews.
          (syn: "Greetings from Telesensory Systems ...")
          Cassette, good quality


1980 TSI shipped a few prototype reading machines, then discon-
     tinued development of the full reading machine product.  The
     text-to-speech component was developed as the Prose 2000
     series.  The Prose 2000 board of 1982 was sold to Kurzweil
     for use in the Kurzweil Reading Machine to replace the
     Kurzweil text-to-speech component (see SSSHP USA Kurzweil
     Computer Products file).


1980 Caldwell, J. L., "Programmable synthesis using a new speech
     microprocessor", ICASSP-80, 868-871 (1980). Digital signal
     processor for formant synthesis.

     ARTIFACT: TTS-X Text-to-Speech prototype, before card level,
               about 1.5 ft x 1.5 ft x 2 ft, three LSI-11
               microprocessors, DEC tape reader for program IPL.
               Possession of G.F. Groner.


1980 Bernstein, J., and D.B. Pisoni, "Unlimited text-to-speech
     system: description and evaluation of a microprocessor-based
     device," Proc. ICASSP-80, 576-579 (1980). Letter-to-sound
     rules. Prose-2000 development system (TTS-X) differences
     from MITalk. (K)

     SSSHP 31 Tape: TSI Demo, J. Bernstein, 11/11/80
           (2:05 min passage, "The purpose of this recording is
            to demonstrate ... Palo Alto, California")
            4" reel 7 1/2 ips, good quality

     SSSHP 33 Tape: "MITalk, TSI Comparisons (Pisoni Tests) 1980",
           by D.B. Pisoni, 9/26/80

          ("Northwind" passage, MITalk. "Estes Chapter", MITalk.
            Modified Rhyme test, 10 trials, MITalk.
            Harvard sentences, 10 trials, MITalk.
            Haskins sentences, 10 trials, MITalk.
           "Lens Buyer" passage, MITalk and TSI.
           "Noise Pollution" passage, MITalk and TSI)
            Cassette, good quality, copy of N.R. Dixon copy, Maxey
            Tape T80.9


1981 Bernstein, J., and L. Nessly, "Performance comparison of
     component algorithms for the phonemicization of
     orthography," Proc. 19th Ann. Assoc. Computational
     Linguistics, Stanford Univ., 19-22 (1981).  Stress rules.
     (K)


1981 Allen, J., "Linguistic-based algorithms offer practical text-
     to-speech systems," Speech Technology 1 (1), 12-16, 1981.
     MITalk-79


1981 "Specifications of Prototype Text-to-Speech System Model
     TTS-X", 1/81. (SSSHP 19 Product Brochures)


1982 Announcement of commercial PROSE 2000 Text-to-Speech
     Converter. Single board priced at $3500 (subsequently $3225).
     PR2020 (PROSE 2000 in cabinet). Later PROSE 4000 (PROSE 2000
     on a IBM Personal Computer board). ASCII text-to-speech.


     Product Brochures (SSSHP 19):

        "PROSE 2000(tm) TEXT-TO-SPEECH CONVERTER", 3/1/82.
        "PROSE 2020 Text-to-Speech Conversion Peripheral"
        "PROSE 4000 Text-to-Speech PC Voice Module"


198? SSSHP 95  Videotape: "Stephen Hawking: The Universe Within",
          tape of physicist Stephen Hawking using a speech synthe-
          sizer to recount his career. MIT Professor Dennis Klatt
          identified the synthesizer as a PROSE 2000 from
          Telesensory Systems, Inc. Videotape was broadcast on
          the Public Broadcasting System. Copy of tape donated by
          Ms. Teri H. Flinchum, Cabisco Teleproductions, Carolina
          Biological Supply Company, Burlington NC, April 10,
          1991.  This tape is proprietary to Carolina Biological
          Supply Co and copies must be obtained from them (see
          SSSHP USA Telesensory Systems, Inc. correspondence for 
          prices).


1982 Groner, G.F., J. Bernstein, E. Ingber, J. Pearlman, and T.
     Toal, "A real-time text-to-speech converter," Speech
     Technology 1 (2), 73-76 (1982).  (K)

     SSSHP 18.2 Tape: PROSE 2000 Text-to-Speech Converter Demon-
          stration V1.0, 4/13/82.
          (syn: "I am the PROSE 2000 text-to-speech converter"...
          long discourse, variations of control, poetry, joke ..
          .. "provide the answers.")
          Cassette, good quality


1983 Speech Plus, Inc. spun off from the Speech Systems Division
     (also known as Telesensory Speech Systems) of Telesensory
     Systems, Inc. PROSE 2000 Version 2.0 was first major
     improvement in speech quality.

     SSSHP 18.3 Tape: PROSE 2000 Version 1.2 to 2.0 Differences,
          5/18/83, A/B comparisons, several samples.
          ("Here is a demonstration of the differences ...")
          Cassette, ok quality (a little bassy)


1984 CallText product family announced. SSSHP 19 Product
     Brochures:

     CallText 5000 Telephone/Voice Module (IBM PC board $3225)
     CallText 5050 RS232 Peripheral (in cabinet, $3900)
     CallText 5100 Multichannel Programmable System (for 5 tele-
        phone lines, $23,670). (In 1987, CallText 5101 was
        replaced by CallText 5104 at $25,595 for 5 telephone
        lines)


1985 Kaplan, G. and E.J. Lerner, "Realism in synthetic speech,"
     IEEE Spectrum 32-37, April 1985. Review of the text-to-speech
     state of the art. Includes diagrams of PROSE 2000 and Speech
     Plus, Inc. text-to-speech conversion steps and vocal tract
     model. Version 3.0 software was the second major improvement
     in speech quality.

     SSSHP 91.12 Tape: "MIT - Demo Tape 1, 10/90"
          (syn, 4 sen: "Four hours of steady work faced us ...  A
          rod is used to catch pink salmon.")
          7" reel, 7.5 ips, good quality, copy of Klatt tape
                  ****  use for master  ****

     SSSHP 32.32 Tape: Demo to accompany "Review of Text-to-speech
          conversion for English," D.H. Klatt, JASA 82.3, Sep 1987.
          (4 sen: "Four hours of steady work faced us... A rod is
          used to catch pink salmon")
          Cassette, Klatt MIT A/D and D/A of SSSHP 91.12


1986 Malsheen, B.J., J.T. Wright, M. Yue and M. Peet, "Intelligi-
     bility of synthetic CVC stimuli over the telephone," 111th
     meeting of the ASA, Cleveland, Ohio, May 1986. Version 3.1
     was the first tuning to improve operation over the telephone.
     (SSSHP 19 paper reprints)

     SSSHP 18.4 Tape: Comparison of CallText 5000 Versions 3.0 and
          3.1 heard over a speaker and over the telephone, 5/22/86.
          ("How San Jose lost ... international airport.")
          Cassette, good quality, -10 VU level


1986 Wright, J.T., B.J. Malsheen and M. Peet, "Comparison of
     segmental intelligibility and pronunciation accuracy for two
     commercial text-to-speech systems," Proc. AVIOS, 235-261,
     1986. (SSSHP 19 reprints)

     SSSHP 18.5 Tape: CallText/PROSE V3.2 demonstration of pro-
          nunciation of homographs and proper names, 10/86.
          Version 3.1 vs Version 3.2.
          (3 sen: "He read the documents ... will be completed.",
           family names: " ... Robaschaux.")
           Cassette, good quality, -10 VU level


1986 Huggins, A.W.F., R.A. Houde, and E. Colwell, "Vidvox human
     factors investigation," Bolt Beranek and Newman Inc., Report
     No. 6187, Cambridge, MA, p. 15 (1986).  Test of 1600 low-
     frequency polysyllabic words. Speech Plus Calltext System:
     8.3% phonemic mispronunciations. DECtalk Vers. 1: 12.9%.  (K)


1986 Malsheen, B.J., J.T. Wright and M. Yue, "Effects of cue
     impoverishment on intelligibility and naturalness of
     synthesized velar stops," 112th meeting of the ASA, Anaheim,
     California, Dec.  1986. (SSSHP 19 paper reprints)


1987 Malsheen, B.J., M. Amador-Hernandez, M.J. Yue, and J.T.
     Wright, "Intelligibility of English, French, German and
     Spanish consonants generated by rule over simulated telephone
     telephone bandwidths", Proc.  XIth Intl.  Congress of
     Phonetic Sciences, 211- 214, 1987. English in production,
     Spanish and German in preliminary testing, French under
     development. (SSSHP 19 paper reprints)

     SSSHP 18.6  Tape: CallText/PROSE multilanguage demonstration,
          5/30/86.
          ("This is a demo tape ... substantially improved.")
          Cassette, good quality, -10 VU level


1988 Announcement of CallText Voice Gateway System at $31650 base
     price.  (SSSHP 19 Product Brochures) Future work will
     improve phonetic quality.


------------------------------------------------------------- Top
BIOGRAPHIES


MARISCELA AMADOR-HERNANDEZ, Senior Linguist

1977 B.A. in linguistics, Escuela Nacional De Antropologia e
     Historia, Mexico City, Mexico
1979 M.A. in linguistics,   "        "            "
1984 Speech Plus, Inc., Mountain View, CA
1986 M.A. in linguistics, Univ. of Calif., Berkeley, CA


SUSAN M. BARBER, Senior Linguist

1976 B.A. in French Linguistics, Univ. of Calif., Santa Barbara, CA
1978 M.A. in general linguistics, Univ. de Paris III, Paris,
     France
1979 Diplome des Etudes Approfondies in phonetics, Univ. d'Aix-
     Marseilles, France
1981 Telesensory Systems, Inc., Palo Alto, CA
1983 Speech Plus, Inc., Mountain View, CA
1987 Infovox AB, Solna, Sweden


JARED BERNSTEIN, Project Leader

1971 B.A. in philosophy, Univ. of Arizona, Tucson, AZ
1975 M.A. in linguistics, Univ. of Michigan, Ann Arbor, MI
1976 Ph.D. in linguistics, Univ. of Michigan, Ann Arbor, MI
     Postdoctoral Fellow, Speech Communication Group, Mass. Inst.
     of Tech., Cambridge, MA
1979 Telesensory Systems, Inc., Palo Alto, CA
1983 Speech Plus, Inc., Mountain View, CA
1984 Speech Research Program, SRI International, Menlo Park,
     CA 94025


JAMES C. BLISS, President, Telesensory Systems, Inc.

1956 B.S. in electrical engineering, Northwestern Univ., Chicago,
     IL
1958 M.S. in electrical engineering, Stanford Univ., Stanford, CA
1961 Ph.D. in electrical engineering, Mass. Inst. of Tech.,
     Cambridge, MA
1965 Stanford Research Institute, Menlo Park, CA
1966 SRI and Assoc. Prof. of EE, Stanford Univ.
1970 President, Telesensory Systems, Inc., Palo Alto, CA
1983 Director, Speech Plus, Inc., Mountain View, CA


JAMES L. CALDWELL, Project Leader

197  Bell Laboratories, Murray Hill, NJ
1976 Telesensory Systems, Inc., Palo Alto, CA
1981 Calma Co., Milpitus, CA
198  Sierra Semiconductor Corp., San Jose, CA
198  VLSI Technology Inc., San Jose, CA


ERIC A. DORSEY, software engineer

1978 B.S. in electrical engineering, Stanford Univ., Stanford, CA,
     Telesensory Systems, Inc., Palo Alto, CA
1983 Speech Plus, Inc., Mountain View, CA
1988 Compression Laboratories, Inc., San Jose, CA


GABRIEL F. GRONER, Vice President, Speech Plus, Inc.

1960 B.S. in engineering, Univ. of California, Los Angeles, CA
1961 M.S. in electrical engineering, Stanford Univ., Stanford, CA
1964 Ph.D.      "            "          "       "       "       "
1964 The Rand Corporation, Santa Monica, CA
1978 Telesensory Systems, Inc., Palo Alto, CA
1980 General Manager, Speech Systems Division, and Vice President,
     Telesensory Systems, Inc., Palo Alto, CA
1983 Vice President, Engineering, Speech Plus, Inc., Mountain
     View, CA
1989 Insight Solutions, Inc.


ED INGBER, hardware project leader

1980 Telesensory Systems, Inc., Palo Alto, CA
1982 Advanced Computer Controls, Sunnyvale, CA


JOHN G. LINVILL

1941 A.B. in mathematics, William Jewell College, Liberty, MO.
1943 B.S. in electrical engineering, Mass. Inst. of Tech,
     Cambridge, MA
1945 M.S. in electrical engineering,  "      "       "
1949 Sc.D. in electrical engineering, Assist. Prof. of EE, MIT
1951 Bell Telephone Laboratories, Murray Hill, NJ
1955 EE Dept., Stanford University, Stanford, CA
1969 Head, EE Dept., "       "          "
1970 Board of Directors, Telesensory Systems, Inc.
19   Director, Center for Integrated Systems, Stanford Univ.


BATHSHEBA J. MALSHEEN, Project Leader, Text-to-Speech project

1971 B.A. in Spanish and English Literature, Hofstra Univ.,
     Hemstead, NY
1975 A.M. in linguistics, Brown Univ., Providence, RI
1979 Ph.D. "     "          "     "         "       "
1983 Speech Plus, Inc., Mountain View, CA


LARRY NESSLY, formerly Univ. of North Carolina


JOE PEARLMAN, software engineer

1967 B.S. in mathematics, Univ. of Michigan, Ann Arbor, MI
1968 M.S. in computer science, Stanford Univ., Stanford, CA
1969 Control Data Corp., San Jose, CA
1979 Telesensory Systems, Inc., Palo Alto, CA
1983 Circadian Systems, Sunnyvale, CA


MARGOT PEET, Linguist

197  B.A., Bryn Mawr College, Bryn Mawr, PA
1988 Ph.D. in linguistics, Univ. of Calif., Berkeley, CA


DAVID B. PISONI  (see SSSHP USA Indiana Univ. file)


TED TOAL, software engineer

1978 Telesensory Systems, Inc., Palo Alto, CA
1982 consultant, Nevada City, CA


MELANIE J. YUE, Linguist

1983 B.A. in social sciences, Univ. of Calif., Santa Barbara, CA
     Speech Plus, Inc., Mountain View, CA
1988 Syn Optics, Mountain View, CA


JAMES T. WRIGHT, Senior Linguist

1969 B.A. in political science, Univ. of Calif., Berkeley, CA
1977 M.A. in linguistics,        "        "         "
1978 Phonetics Laboratory,       "        "         "
1980 Berkeley Systems Works, Berkeley, CA
1982 Applied Speech Technology, Berkeley, CA
1984 Speech Plus, Inc., Mountain View, CA
1987
1988 Sun Microsystems, Mountain View, CA
 
 
------------------------------------------------------------- Top
CONTRIBUTIONS AND REVIEW BY:

Dr. Gabriel F. Groner  (1989)
Speech Plus, Inc.
 
SSSHP Contents | Labs | Abbr. | Index

Smithsonian Speech Synthesis History Project
National Museum of American History | Archives Center
Smithsonian Institution | Privacy | Terms of Use