PERCEPTUAL EVALUATION OF MITALK: THE MIT UNRESTRICTED TEXT-TO-SPEECH SYSTEM.

David Pisoni, Sharon Hunnicutt

Research output: Chapter in Book/Report/Conference proceedingChapter

37 Citations (Scopus)

Abstract

A detailed perceptual evaluation of MITalk has been carried out to obtain measures of intelligibility and comprehension of the synthetic speech produced by the system. Phoneme recognition as measured by the Modified Rhyme Test showed an average error rate of only 6. 9% overall. Correct word recognition assessed with a set of Harvard psychoacoustic sentences was 93. 2% whereas performance with a set of semantically anomalous sentences developed at Haskins Laboratories was 78. 7%. Comprehension performance on multiple-choice questions designed to assess understanding of continuous fluent synthetic speech showed good-to-excellent levels of performance and continued improvement over time.

Original languageEnglish
Title of host publicationRecord - IEEE International Conference on Acoustics, Speech & Signal Processing
PublisherIEEE
Pages572-575
Number of pages4
Volume2
StatePublished - 1980
Externally publishedYes
EventUnknown conference - Denver, CO, USA
Duration: Apr 9 1980Apr 11 1980

Other

OtherUnknown conference
CityDenver, CO, USA
Period4/9/804/11/80

Fingerprint

Speech intelligibility

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Pisoni, D., & Hunnicutt, S. (1980). PERCEPTUAL EVALUATION OF MITALK: THE MIT UNRESTRICTED TEXT-TO-SPEECH SYSTEM. In Record - IEEE International Conference on Acoustics, Speech & Signal Processing (Vol. 2, pp. 572-575). IEEE.

PERCEPTUAL EVALUATION OF MITALK : THE MIT UNRESTRICTED TEXT-TO-SPEECH SYSTEM. / Pisoni, David; Hunnicutt, Sharon.

Record - IEEE International Conference on Acoustics, Speech & Signal Processing. Vol. 2 IEEE, 1980. p. 572-575.

Research output: Chapter in Book/Report/Conference proceedingChapter

Pisoni, D & Hunnicutt, S 1980, PERCEPTUAL EVALUATION OF MITALK: THE MIT UNRESTRICTED TEXT-TO-SPEECH SYSTEM. in Record - IEEE International Conference on Acoustics, Speech & Signal Processing. vol. 2, IEEE, pp. 572-575, Unknown conference, Denver, CO, USA, 4/9/80.
Pisoni D, Hunnicutt S. PERCEPTUAL EVALUATION OF MITALK: THE MIT UNRESTRICTED TEXT-TO-SPEECH SYSTEM. In Record - IEEE International Conference on Acoustics, Speech & Signal Processing. Vol. 2. IEEE. 1980. p. 572-575
Pisoni, David ; Hunnicutt, Sharon. / PERCEPTUAL EVALUATION OF MITALK : THE MIT UNRESTRICTED TEXT-TO-SPEECH SYSTEM. Record - IEEE International Conference on Acoustics, Speech & Signal Processing. Vol. 2 IEEE, 1980. pp. 572-575
@inbook{b90df1655e84472bb967326f47a6cf4e,
title = "PERCEPTUAL EVALUATION OF MITALK: THE MIT UNRESTRICTED TEXT-TO-SPEECH SYSTEM.",
abstract = "A detailed perceptual evaluation of MITalk has been carried out to obtain measures of intelligibility and comprehension of the synthetic speech produced by the system. Phoneme recognition as measured by the Modified Rhyme Test showed an average error rate of only 6. 9{\%} overall. Correct word recognition assessed with a set of Harvard psychoacoustic sentences was 93. 2{\%} whereas performance with a set of semantically anomalous sentences developed at Haskins Laboratories was 78. 7{\%}. Comprehension performance on multiple-choice questions designed to assess understanding of continuous fluent synthetic speech showed good-to-excellent levels of performance and continued improvement over time.",
author = "David Pisoni and Sharon Hunnicutt",
year = "1980",
language = "English",
volume = "2",
pages = "572--575",
booktitle = "Record - IEEE International Conference on Acoustics, Speech & Signal Processing",
publisher = "IEEE",

}

TY - CHAP

T1 - PERCEPTUAL EVALUATION OF MITALK

T2 - THE MIT UNRESTRICTED TEXT-TO-SPEECH SYSTEM.

AU - Pisoni, David

AU - Hunnicutt, Sharon

PY - 1980

Y1 - 1980

N2 - A detailed perceptual evaluation of MITalk has been carried out to obtain measures of intelligibility and comprehension of the synthetic speech produced by the system. Phoneme recognition as measured by the Modified Rhyme Test showed an average error rate of only 6. 9% overall. Correct word recognition assessed with a set of Harvard psychoacoustic sentences was 93. 2% whereas performance with a set of semantically anomalous sentences developed at Haskins Laboratories was 78. 7%. Comprehension performance on multiple-choice questions designed to assess understanding of continuous fluent synthetic speech showed good-to-excellent levels of performance and continued improvement over time.

AB - A detailed perceptual evaluation of MITalk has been carried out to obtain measures of intelligibility and comprehension of the synthetic speech produced by the system. Phoneme recognition as measured by the Modified Rhyme Test showed an average error rate of only 6. 9% overall. Correct word recognition assessed with a set of Harvard psychoacoustic sentences was 93. 2% whereas performance with a set of semantically anomalous sentences developed at Haskins Laboratories was 78. 7%. Comprehension performance on multiple-choice questions designed to assess understanding of continuous fluent synthetic speech showed good-to-excellent levels of performance and continued improvement over time.

UR - http://www.scopus.com/inward/record.url?scp=0019221277&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0019221277&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:0019221277

VL - 2

SP - 572

EP - 575

BT - Record - IEEE International Conference on Acoustics, Speech & Signal Processing

PB - IEEE

ER -