Using word spotting to evaluate ROILA : a speech recognition friendly artificial language

Omar Mubin; Christoph Bartneck; Loe Feijs

doi:10.1145/1753846.1753973

Using word spotting to evaluate ROILA : a speech recognition friendly artificial language

Omar Mubin, Christoph Bartneck, Loe Feijs

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

2 Citations (Scopus)

Abstract

![CDATA[In our research we argue for the benefits that an artificial language could provide to improve the accuracy of speech recognition. We briefly present the design and implementation of a vocabulary of our intended artificial language (ROILA), the latter by means of a genetic algorithm that attempted to generate words which would have low likelihood of being confused by a speech recognizer. Lastly we discuss the methodology and results of two word spotting experiments that were carried out to evaluate if indeed the vocabulary of ROILA achieved better recognition than English. Our results reveal that our initial vocabulary was not significantly better than English but when the vocabulary was modified to include CV-type words only, the vocabulary nearly significantly outperformed English.]]

Original language	English
Title of host publication	Proceedings of the 28th Annual CHI Conference on Human Factors in Computing Systems (CHI2010): Atlanta, Ga, USA, April 12-15, 2010
Publisher	SIGCHI
Pages	3289-3294
Number of pages	6
ISBN (Print)	9781605589312
DOIs	https://doi.org/10.1145/1753846.1753973
Publication status	Published - 2010
Event	CHI Conference - Duration: 26 Apr 2014 → …

Conference

Conference	CHI Conference
Period	26/04/14 → …

Access to Document

10.1145/1753846.1753973

Cite this

@inproceedings{37a030b13ff743d39ec9e1741b27e63a,

title = "Using word spotting to evaluate ROILA : a speech recognition friendly artificial language",

abstract = "![CDATA[In our research we argue for the benefits that an artificial language could provide to improve the accuracy of speech recognition. We briefly present the design and implementation of a vocabulary of our intended artificial language (ROILA), the latter by means of a genetic algorithm that attempted to generate words which would have low likelihood of being confused by a speech recognizer. Lastly we discuss the methodology and results of two word spotting experiments that were carried out to evaluate if indeed the vocabulary of ROILA achieved better recognition than English. Our results reveal that our initial vocabulary was not significantly better than English but when the vocabulary was modified to include CV-type words only, the vocabulary nearly significantly outperformed English.]]",

author = "Omar Mubin and Christoph Bartneck and Loe Feijs",

year = "2010",

doi = "10.1145/1753846.1753973",

language = "English",

isbn = "9781605589312",

pages = "3289--3294",

booktitle = "Proceedings of the 28th Annual CHI Conference on Human Factors in Computing Systems (CHI2010): Atlanta, Ga, USA, April 12-15, 2010",

publisher = "SIGCHI",

note = "CHI Conference ; Conference date: 26-04-2014",

}

Using word spotting to evaluate ROILA : a speech recognition friendly artificial language. / Mubin, Omar; Bartneck, Christoph; Feijs, Loe.
Proceedings of the 28th Annual CHI Conference on Human Factors in Computing Systems (CHI2010): Atlanta, Ga, USA, April 12-15, 2010. SIGCHI, 2010. p. 3289-3294.

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

TY - GEN

T1 - Using word spotting to evaluate ROILA : a speech recognition friendly artificial language

AU - Mubin, Omar

AU - Bartneck, Christoph

AU - Feijs, Loe

PY - 2010

Y1 - 2010

N2 - ![CDATA[In our research we argue for the benefits that an artificial language could provide to improve the accuracy of speech recognition. We briefly present the design and implementation of a vocabulary of our intended artificial language (ROILA), the latter by means of a genetic algorithm that attempted to generate words which would have low likelihood of being confused by a speech recognizer. Lastly we discuss the methodology and results of two word spotting experiments that were carried out to evaluate if indeed the vocabulary of ROILA achieved better recognition than English. Our results reveal that our initial vocabulary was not significantly better than English but when the vocabulary was modified to include CV-type words only, the vocabulary nearly significantly outperformed English.]]

AB - ![CDATA[In our research we argue for the benefits that an artificial language could provide to improve the accuracy of speech recognition. We briefly present the design and implementation of a vocabulary of our intended artificial language (ROILA), the latter by means of a genetic algorithm that attempted to generate words which would have low likelihood of being confused by a speech recognizer. Lastly we discuss the methodology and results of two word spotting experiments that were carried out to evaluate if indeed the vocabulary of ROILA achieved better recognition than English. Our results reveal that our initial vocabulary was not significantly better than English but when the vocabulary was modified to include CV-type words only, the vocabulary nearly significantly outperformed English.]]

UR - http://handle.uws.edu.au:8081/1959.7/562597

UR - http://www.chi2010.org/index.html

U2 - 10.1145/1753846.1753973

DO - 10.1145/1753846.1753973

M3 - Conference Paper

SN - 9781605589312

SP - 3289

EP - 3294

BT - Proceedings of the 28th Annual CHI Conference on Human Factors in Computing Systems (CHI2010): Atlanta, Ga, USA, April 12-15, 2010

PB - SIGCHI

T2 - CHI Conference

Y2 - 26 April 2014

ER -

Using word spotting to evaluate ROILA : a speech recognition friendly artificial language

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this