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

O. Mubin; C. Bartneck; L.M.G. Feijs

doi:10.1145/1753846.1753973

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

O. Mubin, C. Bartneck, L.M.G. Feijs

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

3 Citations (Scopus)

Abstract

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 of the International Conference extended abstracts on Human factors in computing systems, April 10-15, 2010, Atlanta, Georgia
Publisher	Association for Computing Machinery, Inc
Pages	3289-3294
ISBN (Print)	978-1-60558-930-5
DOIs	https://doi.org/10.1145/1753846.1753973
Publication status	Published - 2010
Event	28th Annual CHI Conference on Human Factors in Computing Systems - Florence, Italy Duration: 5 Apr 2008 → 10 Apr 2008 Conference number: 28 http://www.chi2010.org/

Conference

Conference	28th Annual CHI Conference on Human Factors in Computing Systems
Abbreviated title	CHI 2010
Country	Italy
City	Florence
Period	5/04/08 → 10/04/08
Internet address	http://www.chi2010.org/

Access to Document

10.1145/1753846.1753973

Fingerprint Dive into the research topics of 'Using word spotting to evaluate ROILA: a speech recognition friendly artificial language'. Together they form a unique fingerprint.

Cite this

Mubin, O., Bartneck, C., & Feijs, L. M. G. (2010). Using word spotting to evaluate ROILA: a speech recognition friendly artificial language. In Proceedings of the 28th of the International Conference extended abstracts on Human factors in computing systems, April 10-15, 2010, Atlanta, Georgia (pp. 3289-3294). Association for Computing Machinery, Inc. https://doi.org/10.1145/1753846.1753973

@inproceedings{2098cd6255704686ba18eeda8f936d16,

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

abstract = "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 = "O. Mubin and C. Bartneck and L.M.G. Feijs",

year = "2010",

doi = "10.1145/1753846.1753973",

language = "English",

isbn = "978-1-60558-930-5",

pages = "3289--3294",

booktitle = "Proceedings of the 28th of the International Conference extended abstracts on Human factors in computing systems, April 10-15, 2010, Atlanta, Georgia",

publisher = "Association for Computing Machinery, Inc",

address = "United States",

note = "28th Annual CHI Conference on Human Factors in Computing Systems, CHI 2010 ; Conference date: 05-04-2008 Through 10-04-2008",

url = "http://www.chi2010.org/",

}

Mubin, O, Bartneck, C & Feijs, LMG 2010, Using word spotting to evaluate ROILA: a speech recognition friendly artificial language. in Proceedings of the 28th of the International Conference extended abstracts on Human factors in computing systems, April 10-15, 2010, Atlanta, Georgia. Association for Computing Machinery, Inc, pp. 3289-3294, 28th Annual CHI Conference on Human Factors in Computing Systems, Florence, Italy, 5/04/08. https://doi.org/10.1145/1753846.1753973

Using word spotting to evaluate ROILA: a speech recognition friendly artificial language. / Mubin, O.; Bartneck, C.; Feijs, L.M.G.

Proceedings of the 28th of the International Conference extended abstracts on Human factors in computing systems, April 10-15, 2010, Atlanta, Georgia. Association for Computing Machinery, Inc, 2010. p. 3289-3294.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

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

AU - Mubin, O.

AU - Bartneck, C.

AU - Feijs, L.M.G.

N1 - Conference code: 28

PY - 2010

Y1 - 2010

N2 - 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 - 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.

U2 - 10.1145/1753846.1753973

DO - 10.1145/1753846.1753973

M3 - Conference contribution

SN - 978-1-60558-930-5

SP - 3289

EP - 3294

BT - Proceedings of the 28th of the International Conference extended abstracts on Human factors in computing systems, April 10-15, 2010, Atlanta, Georgia

PB - Association for Computing Machinery, Inc

T2 - 28th Annual CHI Conference on Human Factors in Computing Systems

Y2 - 5 April 2008 through 10 April 2008

ER -

Mubin O, Bartneck C, Feijs LMG. Using word spotting to evaluate ROILA: a speech recognition friendly artificial language. In Proceedings of the 28th of the International Conference extended abstracts on Human factors in computing systems, April 10-15, 2010, Atlanta, Georgia. Association for Computing Machinery, Inc. 2010. p. 3289-3294 https://doi.org/10.1145/1753846.1753973