Computer- and human-directed speech before and after correction

Denis Burnham; Sebastian Joeffry; Lauren Rice

Computer- and human-directed speech before and after correction

Denis Burnham, Sebastian Joeffry, Lauren Rice

Research output: Chapter in Book / Conference Paper › Conference Paper

Abstract

Speech register research shows that humans are adept at finetuning components of their speech to accommodate the needs audience of the audience, suggesting that they have a model of human communication needs. However, when that audience is a computer rather than another human, such a model may be invalid. Here we examine humans' speech to other humans or an auditory-visual avatar before and after the computer or the human listener makes a listening "error". Speech is found to be hyperarticulated in Computer- compared with Human- Directed speech, and also in speech after correction. Results are discussed in terms of human-computer interaction and ASR systems.

Original language	English
Title of host publication	Proceedings of the 13th Australasian International Conference on Speech Science and Technology, 14-16 December 2010, Melbourne, Australia
Publisher	ASSTA
Pages	13-17
Number of pages	5
ISBN (Print)	9780958194631
Publication status	Published - 2010
Event	Australasian International Conference on Speech Science and Technology - Duration: 3 Dec 2012 → …

Conference

Conference	Australasian International Conference on Speech Science and Technology
Period	3/12/12 → …

Keywords

human-computer interaction
speech

Cite this

@inproceedings{9855876e7f1f4e35a80da222200022de,

title = "Computer- and human-directed speech before and after correction",

abstract = "Speech register research shows that humans are adept at finetuning components of their speech to accommodate the needs audience of the audience, suggesting that they have a model of human communication needs. However, when that audience is a computer rather than another human, such a model may be invalid. Here we examine humans' speech to other humans or an auditory-visual avatar before and after the computer or the human listener makes a listening {"}error{"}. Speech is found to be hyperarticulated in Computer- compared with Human- Directed speech, and also in speech after correction. Results are discussed in terms of human-computer interaction and ASR systems.",

keywords = "human-computer interaction, speech",

author = "Denis Burnham and Sebastian Joeffry and Lauren Rice",

year = "2010",

language = "English",

isbn = "9780958194631",

pages = "13--17",

booktitle = "Proceedings of the 13th Australasian International Conference on Speech Science and Technology, 14-16 December 2010, Melbourne, Australia",

publisher = "ASSTA",

note = "Australasian International Conference on Speech Science and Technology ; Conference date: 03-12-2012",

}

TY - GEN

T1 - Computer- and human-directed speech before and after correction

AU - Burnham, Denis

AU - Joeffry, Sebastian

AU - Rice, Lauren

PY - 2010

Y1 - 2010

N2 - Speech register research shows that humans are adept at finetuning components of their speech to accommodate the needs audience of the audience, suggesting that they have a model of human communication needs. However, when that audience is a computer rather than another human, such a model may be invalid. Here we examine humans' speech to other humans or an auditory-visual avatar before and after the computer or the human listener makes a listening "error". Speech is found to be hyperarticulated in Computer- compared with Human- Directed speech, and also in speech after correction. Results are discussed in terms of human-computer interaction and ASR systems.

AB - Speech register research shows that humans are adept at finetuning components of their speech to accommodate the needs audience of the audience, suggesting that they have a model of human communication needs. However, when that audience is a computer rather than another human, such a model may be invalid. Here we examine humans' speech to other humans or an auditory-visual avatar before and after the computer or the human listener makes a listening "error". Speech is found to be hyperarticulated in Computer- compared with Human- Directed speech, and also in speech after correction. Results are discussed in terms of human-computer interaction and ASR systems.

KW - human-computer interaction

KW - speech

UR - http://handle.uws.edu.au:8081/1959.7/504796

M3 - Conference Paper

SN - 9780958194631

SP - 13

EP - 17

BT - Proceedings of the 13th Australasian International Conference on Speech Science and Technology, 14-16 December 2010, Melbourne, Australia

PB - ASSTA

T2 - Australasian International Conference on Speech Science and Technology

Y2 - 3 December 2012

ER -

Computer- and human-directed speech before and after correction

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this