Assessing automatic speech recognition in measuring speech intelligibility

A study of Malay speakers with speech impairments

Fadhilah Rosdi, Mumtaz Begum Mustafa, Siti Salwah Salim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper investigates the potential of Automatic Speech Recognition application in measuring the speech intelligibility of speech impaired speakers. ASR has been suggested to be a useful way of intelligibility measures in the literature. In this research, we tested ASR's performance in measuring speech intelligibility in the context of speakers with speech impairments. A speaker independent ASR system was developed to produce the intelligibility scores automatically. A panel of Speech Language Pathologists involved in assessing the speech intelligibility subjectively to provide the benchmark scores. Results show that the correlation between ASR with SLPs subjective scores is significant at p<0.0f, r(0.57) = 0.1. This indicates a positive correlation of ASR automatic measurement with human subjective rating, which the WRA increase with the increment of intelligibility scores.

Original languageEnglish
Title of host publicationProceedings of the 2017 6th International Conference on Electrical Engineering and Informatics
Subtitle of host publicationSustainable Society Through Digital Innovation, ICEEI 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-6
Number of pages6
Volume2017-November
ISBN (Electronic)9781538604755
DOIs
Publication statusPublished - 9 Mar 2018
Event6th International Conference on Electrical Engineering and Informatics, ICEEI 2017 - Langkawi, Malaysia
Duration: 25 Nov 201727 Nov 2017

Other

Other6th International Conference on Electrical Engineering and Informatics, ICEEI 2017
CountryMalaysia
CityLangkawi
Period25/11/1727/11/17

Fingerprint

Speech Intelligibility
Speech intelligibility
Automatic Speech Recognition
Speech recognition
Benchmarking
Increment
Language
Benchmark
Speech
Research

Keywords

  • automatic speech recognition
  • speech impairments
  • speech intelligibility

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Optimization
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Information Systems
  • Software
  • Electrical and Electronic Engineering
  • Health Informatics

Cite this

Rosdi, F., Mustafa, M. B., & Salim, S. S. (2018). Assessing automatic speech recognition in measuring speech intelligibility: A study of Malay speakers with speech impairments. In Proceedings of the 2017 6th International Conference on Electrical Engineering and Informatics: Sustainable Society Through Digital Innovation, ICEEI 2017 (Vol. 2017-November, pp. 1-6). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICEEI.2017.8312396

Assessing automatic speech recognition in measuring speech intelligibility : A study of Malay speakers with speech impairments. / Rosdi, Fadhilah; Mustafa, Mumtaz Begum; Salim, Siti Salwah.

Proceedings of the 2017 6th International Conference on Electrical Engineering and Informatics: Sustainable Society Through Digital Innovation, ICEEI 2017. Vol. 2017-November Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-6.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Rosdi, F, Mustafa, MB & Salim, SS 2018, Assessing automatic speech recognition in measuring speech intelligibility: A study of Malay speakers with speech impairments. in Proceedings of the 2017 6th International Conference on Electrical Engineering and Informatics: Sustainable Society Through Digital Innovation, ICEEI 2017. vol. 2017-November, Institute of Electrical and Electronics Engineers Inc., pp. 1-6, 6th International Conference on Electrical Engineering and Informatics, ICEEI 2017, Langkawi, Malaysia, 25/11/17. https://doi.org/10.1109/ICEEI.2017.8312396
Rosdi F, Mustafa MB, Salim SS. Assessing automatic speech recognition in measuring speech intelligibility: A study of Malay speakers with speech impairments. In Proceedings of the 2017 6th International Conference on Electrical Engineering and Informatics: Sustainable Society Through Digital Innovation, ICEEI 2017. Vol. 2017-November. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-6 https://doi.org/10.1109/ICEEI.2017.8312396
Rosdi, Fadhilah ; Mustafa, Mumtaz Begum ; Salim, Siti Salwah. / Assessing automatic speech recognition in measuring speech intelligibility : A study of Malay speakers with speech impairments. Proceedings of the 2017 6th International Conference on Electrical Engineering and Informatics: Sustainable Society Through Digital Innovation, ICEEI 2017. Vol. 2017-November Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-6
@inproceedings{5ce9f2484ffb44fc8c76f7352d260183,
title = "Assessing automatic speech recognition in measuring speech intelligibility: A study of Malay speakers with speech impairments",
abstract = "This paper investigates the potential of Automatic Speech Recognition application in measuring the speech intelligibility of speech impaired speakers. ASR has been suggested to be a useful way of intelligibility measures in the literature. In this research, we tested ASR's performance in measuring speech intelligibility in the context of speakers with speech impairments. A speaker independent ASR system was developed to produce the intelligibility scores automatically. A panel of Speech Language Pathologists involved in assessing the speech intelligibility subjectively to provide the benchmark scores. Results show that the correlation between ASR with SLPs subjective scores is significant at p<0.0f, r(0.57) = 0.1. This indicates a positive correlation of ASR automatic measurement with human subjective rating, which the WRA increase with the increment of intelligibility scores.",
keywords = "automatic speech recognition, speech impairments, speech intelligibility",
author = "Fadhilah Rosdi and Mustafa, {Mumtaz Begum} and Salim, {Siti Salwah}",
year = "2018",
month = "3",
day = "9",
doi = "10.1109/ICEEI.2017.8312396",
language = "English",
volume = "2017-November",
pages = "1--6",
booktitle = "Proceedings of the 2017 6th International Conference on Electrical Engineering and Informatics",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Assessing automatic speech recognition in measuring speech intelligibility

T2 - A study of Malay speakers with speech impairments

AU - Rosdi, Fadhilah

AU - Mustafa, Mumtaz Begum

AU - Salim, Siti Salwah

PY - 2018/3/9

Y1 - 2018/3/9

N2 - This paper investigates the potential of Automatic Speech Recognition application in measuring the speech intelligibility of speech impaired speakers. ASR has been suggested to be a useful way of intelligibility measures in the literature. In this research, we tested ASR's performance in measuring speech intelligibility in the context of speakers with speech impairments. A speaker independent ASR system was developed to produce the intelligibility scores automatically. A panel of Speech Language Pathologists involved in assessing the speech intelligibility subjectively to provide the benchmark scores. Results show that the correlation between ASR with SLPs subjective scores is significant at p<0.0f, r(0.57) = 0.1. This indicates a positive correlation of ASR automatic measurement with human subjective rating, which the WRA increase with the increment of intelligibility scores.

AB - This paper investigates the potential of Automatic Speech Recognition application in measuring the speech intelligibility of speech impaired speakers. ASR has been suggested to be a useful way of intelligibility measures in the literature. In this research, we tested ASR's performance in measuring speech intelligibility in the context of speakers with speech impairments. A speaker independent ASR system was developed to produce the intelligibility scores automatically. A panel of Speech Language Pathologists involved in assessing the speech intelligibility subjectively to provide the benchmark scores. Results show that the correlation between ASR with SLPs subjective scores is significant at p<0.0f, r(0.57) = 0.1. This indicates a positive correlation of ASR automatic measurement with human subjective rating, which the WRA increase with the increment of intelligibility scores.

KW - automatic speech recognition

KW - speech impairments

KW - speech intelligibility

UR - http://www.scopus.com/inward/record.url?scp=85050719551&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050719551&partnerID=8YFLogxK

U2 - 10.1109/ICEEI.2017.8312396

DO - 10.1109/ICEEI.2017.8312396

M3 - Conference contribution

VL - 2017-November

SP - 1

EP - 6

BT - Proceedings of the 2017 6th International Conference on Electrical Engineering and Informatics

PB - Institute of Electrical and Electronics Engineers Inc.

ER -