PERCEPTION OF SYNTHETIC SPEECH GENERATED BY RULE.

David Pisoni, Howard C. Nusbaum, Beth G. Greene

Research output: Contribution to journalArticle

63 Citations (Scopus)

Abstract

It is pointed out that the selection of a specific voice response system for a particular application depends on a wide variety of factors, only one of which is the inherent intelligibility of the speech generated by the synthesis routines. The results of several studies that applied measures of phoneme intelligibility, word recognition, and comprehension to assess the perception of synthetic speech are described. Several techniques were used to compare the performance of different synthesis systems with natural speech and to learn more about how humans perceive synthetic speech generated by rule. The findings suggest that the perception of synthetic speech depends on an interaction of several factors including the acoustic-phonetic properties of the speech signal, the requirements of the perceptual task, and the previous experience of the listener. Differences in perception between natural speech and high-quality synthetic speech appear to be related to the redundancy of the acoustic-phonetic information encoded in the speech signal.

Original languageEnglish
Pages (from-to)1665-1676
Number of pages12
JournalProceedings of the IEEE
Volume73
Issue number11
DOIs
StatePublished - Nov 1985

Fingerprint

Speech analysis
Acoustics
Speech intelligibility
Redundancy

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

PERCEPTION OF SYNTHETIC SPEECH GENERATED BY RULE. / Pisoni, David; Nusbaum, Howard C.; Greene, Beth G.

In: Proceedings of the IEEE, Vol. 73, No. 11, 11.1985, p. 1665-1676.

Research output: Contribution to journalArticle

Pisoni, David ; Nusbaum, Howard C. ; Greene, Beth G. / PERCEPTION OF SYNTHETIC SPEECH GENERATED BY RULE. In: Proceedings of the IEEE. 1985 ; Vol. 73, No. 11. pp. 1665-1676.
@article{050fee65b10f47f9b7b8c0272cf5adae,
title = "PERCEPTION OF SYNTHETIC SPEECH GENERATED BY RULE.",
abstract = "It is pointed out that the selection of a specific voice response system for a particular application depends on a wide variety of factors, only one of which is the inherent intelligibility of the speech generated by the synthesis routines. The results of several studies that applied measures of phoneme intelligibility, word recognition, and comprehension to assess the perception of synthetic speech are described. Several techniques were used to compare the performance of different synthesis systems with natural speech and to learn more about how humans perceive synthetic speech generated by rule. The findings suggest that the perception of synthetic speech depends on an interaction of several factors including the acoustic-phonetic properties of the speech signal, the requirements of the perceptual task, and the previous experience of the listener. Differences in perception between natural speech and high-quality synthetic speech appear to be related to the redundancy of the acoustic-phonetic information encoded in the speech signal.",
author = "David Pisoni and Nusbaum, {Howard C.} and Greene, {Beth G.}",
year = "1985",
month = "11",
doi = "10.1109/PROC.1985.13346",
language = "English",
volume = "73",
pages = "1665--1676",
journal = "Proceedings of the IEEE",
issn = "0018-9219",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "11",

}

TY - JOUR

T1 - PERCEPTION OF SYNTHETIC SPEECH GENERATED BY RULE.

AU - Pisoni, David

AU - Nusbaum, Howard C.

AU - Greene, Beth G.

PY - 1985/11

Y1 - 1985/11

N2 - It is pointed out that the selection of a specific voice response system for a particular application depends on a wide variety of factors, only one of which is the inherent intelligibility of the speech generated by the synthesis routines. The results of several studies that applied measures of phoneme intelligibility, word recognition, and comprehension to assess the perception of synthetic speech are described. Several techniques were used to compare the performance of different synthesis systems with natural speech and to learn more about how humans perceive synthetic speech generated by rule. The findings suggest that the perception of synthetic speech depends on an interaction of several factors including the acoustic-phonetic properties of the speech signal, the requirements of the perceptual task, and the previous experience of the listener. Differences in perception between natural speech and high-quality synthetic speech appear to be related to the redundancy of the acoustic-phonetic information encoded in the speech signal.

AB - It is pointed out that the selection of a specific voice response system for a particular application depends on a wide variety of factors, only one of which is the inherent intelligibility of the speech generated by the synthesis routines. The results of several studies that applied measures of phoneme intelligibility, word recognition, and comprehension to assess the perception of synthetic speech are described. Several techniques were used to compare the performance of different synthesis systems with natural speech and to learn more about how humans perceive synthetic speech generated by rule. The findings suggest that the perception of synthetic speech depends on an interaction of several factors including the acoustic-phonetic properties of the speech signal, the requirements of the perceptual task, and the previous experience of the listener. Differences in perception between natural speech and high-quality synthetic speech appear to be related to the redundancy of the acoustic-phonetic information encoded in the speech signal.

UR - http://www.scopus.com/inward/record.url?scp=0022148789&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0022148789&partnerID=8YFLogxK

U2 - 10.1109/PROC.1985.13346

DO - 10.1109/PROC.1985.13346

M3 - Article

AN - SCOPUS:0022148789

VL - 73

SP - 1665

EP - 1676

JO - Proceedings of the IEEE

JF - Proceedings of the IEEE

SN - 0018-9219

IS - 11

ER -