History of speech synthesis

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

For the past two centuries or more, devices capable of generating artificial or synthetic speech have been developed and used to investigate phonetic phenomena. Early systems built in the late 18th and early 19th centuries were mechanical constructions whose components essentially formed a simulation of the human larynx and vocal tract. They served as a demonstration that speech production could be understood as a physical system, a concept that was largely hypothetical at the time. In addition, the modest success of these devices to synthesize artificial, but humanlike speech gave promise that, with adequate control, a machine could potentially be used to "talk" for persons with speech impairments. In the early to mid-20th century, the advent of electrical systems brought about a major change in synthetic speaking devices. Using combinations of circuit elements as analogies to mechanical structures, or to form filters, allowed for greater complexity and more flexible control of the characteristics of speech. During this period, speech synthesizers based on filter banks, resonators, or transmission lines, along with the development of the sound spectrograph, were used to investigate many aspects of speech production and perception. The course of speech synthesis was altered again with digital technology. No longer did synthesizers need to be "built" as real physical machines or with racks of electrical equipment. The entire synthesizer could now be realized as an algorithm with computational instructions. While many digital synthesizers are essentially computational versions of the electrical synthesizers, algorithms allowed for remarkable improvements, enhancements, and new ways of synthesizing speech. This chapter provides a brief history of synthetic speech systems, including mechanical, electrical, and digital types. The primary goal, however, is not to reiterate the details of constructing specific synthesizers but rather to focus on how various synthesis paradigms have facilitated research in phonetics.

Original languageEnglish (US)
Title of host publicationThe Routledge Handbook of Phonetics
PublisherTaylor and Francis
Pages9-33
Number of pages25
ISBN (Electronic)9780429508561
ISBN (Print)9781138648333
DOIs
StatePublished - Jan 1 2019

Fingerprint

history
phonetics
History
Speech Synthesis
Synthesizer
speaking
bank
paradigm
instruction
simulation
human being
Computational
Filter
Speech Production
Artificial
Physical

ASJC Scopus subject areas

  • Arts and Humanities(all)
  • Social Sciences(all)

Cite this

Story, B. H. (2019). History of speech synthesis. In The Routledge Handbook of Phonetics (pp. 9-33). Taylor and Francis. https://doi.org/10.4324/9780429056253-2

History of speech synthesis. / Story, Brad H.

The Routledge Handbook of Phonetics. Taylor and Francis, 2019. p. 9-33.

Research output: Chapter in Book/Report/Conference proceedingChapter

Story, BH 2019, History of speech synthesis. in The Routledge Handbook of Phonetics. Taylor and Francis, pp. 9-33. https://doi.org/10.4324/9780429056253-2
Story BH. History of speech synthesis. In The Routledge Handbook of Phonetics. Taylor and Francis. 2019. p. 9-33 https://doi.org/10.4324/9780429056253-2
Story, Brad H. / History of speech synthesis. The Routledge Handbook of Phonetics. Taylor and Francis, 2019. pp. 9-33
@inbook{1b07a3f858d245c6a0fdfbc9772f0cb6,
title = "History of speech synthesis",
abstract = "For the past two centuries or more, devices capable of generating artificial or synthetic speech have been developed and used to investigate phonetic phenomena. Early systems built in the late 18th and early 19th centuries were mechanical constructions whose components essentially formed a simulation of the human larynx and vocal tract. They served as a demonstration that speech production could be understood as a physical system, a concept that was largely hypothetical at the time. In addition, the modest success of these devices to synthesize artificial, but humanlike speech gave promise that, with adequate control, a machine could potentially be used to {"}talk{"} for persons with speech impairments. In the early to mid-20th century, the advent of electrical systems brought about a major change in synthetic speaking devices. Using combinations of circuit elements as analogies to mechanical structures, or to form filters, allowed for greater complexity and more flexible control of the characteristics of speech. During this period, speech synthesizers based on filter banks, resonators, or transmission lines, along with the development of the sound spectrograph, were used to investigate many aspects of speech production and perception. The course of speech synthesis was altered again with digital technology. No longer did synthesizers need to be {"}built{"} as real physical machines or with racks of electrical equipment. The entire synthesizer could now be realized as an algorithm with computational instructions. While many digital synthesizers are essentially computational versions of the electrical synthesizers, algorithms allowed for remarkable improvements, enhancements, and new ways of synthesizing speech. This chapter provides a brief history of synthetic speech systems, including mechanical, electrical, and digital types. The primary goal, however, is not to reiterate the details of constructing specific synthesizers but rather to focus on how various synthesis paradigms have facilitated research in phonetics.",
author = "Story, {Brad H}",
year = "2019",
month = "1",
day = "1",
doi = "10.4324/9780429056253-2",
language = "English (US)",
isbn = "9781138648333",
pages = "9--33",
booktitle = "The Routledge Handbook of Phonetics",
publisher = "Taylor and Francis",

}

TY - CHAP

T1 - History of speech synthesis

AU - Story, Brad H

PY - 2019/1/1

Y1 - 2019/1/1

N2 - For the past two centuries or more, devices capable of generating artificial or synthetic speech have been developed and used to investigate phonetic phenomena. Early systems built in the late 18th and early 19th centuries were mechanical constructions whose components essentially formed a simulation of the human larynx and vocal tract. They served as a demonstration that speech production could be understood as a physical system, a concept that was largely hypothetical at the time. In addition, the modest success of these devices to synthesize artificial, but humanlike speech gave promise that, with adequate control, a machine could potentially be used to "talk" for persons with speech impairments. In the early to mid-20th century, the advent of electrical systems brought about a major change in synthetic speaking devices. Using combinations of circuit elements as analogies to mechanical structures, or to form filters, allowed for greater complexity and more flexible control of the characteristics of speech. During this period, speech synthesizers based on filter banks, resonators, or transmission lines, along with the development of the sound spectrograph, were used to investigate many aspects of speech production and perception. The course of speech synthesis was altered again with digital technology. No longer did synthesizers need to be "built" as real physical machines or with racks of electrical equipment. The entire synthesizer could now be realized as an algorithm with computational instructions. While many digital synthesizers are essentially computational versions of the electrical synthesizers, algorithms allowed for remarkable improvements, enhancements, and new ways of synthesizing speech. This chapter provides a brief history of synthetic speech systems, including mechanical, electrical, and digital types. The primary goal, however, is not to reiterate the details of constructing specific synthesizers but rather to focus on how various synthesis paradigms have facilitated research in phonetics.

AB - For the past two centuries or more, devices capable of generating artificial or synthetic speech have been developed and used to investigate phonetic phenomena. Early systems built in the late 18th and early 19th centuries were mechanical constructions whose components essentially formed a simulation of the human larynx and vocal tract. They served as a demonstration that speech production could be understood as a physical system, a concept that was largely hypothetical at the time. In addition, the modest success of these devices to synthesize artificial, but humanlike speech gave promise that, with adequate control, a machine could potentially be used to "talk" for persons with speech impairments. In the early to mid-20th century, the advent of electrical systems brought about a major change in synthetic speaking devices. Using combinations of circuit elements as analogies to mechanical structures, or to form filters, allowed for greater complexity and more flexible control of the characteristics of speech. During this period, speech synthesizers based on filter banks, resonators, or transmission lines, along with the development of the sound spectrograph, were used to investigate many aspects of speech production and perception. The course of speech synthesis was altered again with digital technology. No longer did synthesizers need to be "built" as real physical machines or with racks of electrical equipment. The entire synthesizer could now be realized as an algorithm with computational instructions. While many digital synthesizers are essentially computational versions of the electrical synthesizers, algorithms allowed for remarkable improvements, enhancements, and new ways of synthesizing speech. This chapter provides a brief history of synthetic speech systems, including mechanical, electrical, and digital types. The primary goal, however, is not to reiterate the details of constructing specific synthesizers but rather to focus on how various synthesis paradigms have facilitated research in phonetics.

UR - http://www.scopus.com/inward/record.url?scp=85069812868&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069812868&partnerID=8YFLogxK

U2 - 10.4324/9780429056253-2

DO - 10.4324/9780429056253-2

M3 - Chapter

AN - SCOPUS:85069812868

SN - 9781138648333

SP - 9

EP - 33

BT - The Routledge Handbook of Phonetics

PB - Taylor and Francis

ER -