Using the data presented in the accompanying paper [Hilkhuysen et al., J. Acoust. Soc. Am. 131, 531–539 (2012)], the ability of six metrics to predict intelligibility of speech in noise before and after noise suppression was studied. The metrics considered were the Speech Intelligibility Index (SII), the fractional Articulation Index (fAI), the coherence intelligibility index based on the mid-levels in speech (CSIImid), an extension of the Normalized Coherence Metric (NCM+), a part of the speech-based envelope power model (pre-sEPSM), and the Short Term Objective Intelligibility measure (STOI). Three of the measures, SII, CSIImid, and NCM+, overpredicted intelligibility after noise reduction, whereas fAI underpredicted these intelligibilities. The pre-sEPSM metric worked well for speech in babble but failed with car noise. STOI gave the best predictions, but overall the size of intelligibility prediction errors were greater than the change in intelligibility caused by noise suppression. Suggestions for improvements of the metrics are discussed.
Skip Nav Destination
Article navigation
January 2014
January 01 2014
Effects of noise suppression on intelligibility. II: An attempt to validate physical metricsa) Available to Purchase
Gaston Hilkhuysen;
Gaston Hilkhuysen
b)
Department of Speech, Language and Hearing Sciences, University College London
, 2 Wakefield Street, London WC1N 1PF, United Kingdom
Search for other works by this author on:
Nikolay Gaubitch;
Nikolay Gaubitch
Electrical and Electronic Engineering Department, Imperial College
, Exhibition Road, London SW7 2BT, United Kingdom
Search for other works by this author on:
Mike Brookes;
Mike Brookes
Electrical and Electronic Engineering Department, Imperial College
, Exhibition Road, London SW7 2BT, United Kingdom
Search for other works by this author on:
Mark Huckvale
Mark Huckvale
Department of Speech, Language and Hearing Sciences, University College London
, 2 Wakefield Street, London WC1N 1PF, United Kingdom
Search for other works by this author on:
Gaston Hilkhuysen
b)
Department of Speech, Language and Hearing Sciences, University College London
, 2 Wakefield Street, London WC1N 1PF, United Kingdom
Nikolay Gaubitch
Electrical and Electronic Engineering Department, Imperial College
, Exhibition Road, London SW7 2BT, United Kingdom
Mike Brookes
Electrical and Electronic Engineering Department, Imperial College
, Exhibition Road, London SW7 2BT, United Kingdom
Mark Huckvale
Department of Speech, Language and Hearing Sciences, University College London
, 2 Wakefield Street, London WC1N 1PF, United Kingdom
b)
Author to whom correspondence should be addressed. Electronic mail: [email protected]
a)
Part of this work was presented at the British Society of Audiology Short Papers Meeting on Experimental Studies of Hearing and Deafness, Southampton UK, 2009.
J. Acoust. Soc. Am. 135, 439–450 (2014)
Article history
Received:
February 10 2013
Accepted:
November 18 2013
Citation
Gaston Hilkhuysen, Nikolay Gaubitch, Mike Brookes, Mark Huckvale; Effects of noise suppression on intelligibility. II: An attempt to validate physical metrics. J. Acoust. Soc. Am. 1 January 2014; 135 (1): 439–450. https://doi.org/10.1121/1.4837238
Download citation file:
Pay-Per-View Access
$40.00
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
Citing articles via
Focality of sound source placement by higher (ninth) order ambisonics and perceptual effects of spectral reproduction errors
Nima Zargarnezhad, Bruno Mesquita, et al.
A survey of sound source localization with deep learning methods
Pierre-Amaury Grumiaux, Srđan Kitić, et al.
Variation in global and intonational pitch settings among black and white speakers of Southern American English
Aini Li, Ruaridh Purse, et al.
Related Content
Can physical metrics identify noise reduction settings that optimize intelligibility?
Proc. Mtgs. Acoust. (May 2013)
Intelligibility prediction for speech mixed with white Gaussian noise at low signal-to-noise ratios
J. Acoust. Soc. Am. (February 2021)
Prediction of speech masking release for fluctuating interferers based on the envelope power signal-to-noise ratio
J. Acoust. Soc. Am. (April 2012)
Envelope and intensity based prediction of psychoacoustic masking and speech intelligibility
J. Acoust. Soc. Am. (August 2016)
The speech-based envelope power spectrum model (sEPSM) family: Development, achievements, and current challenges
J. Acoust. Soc. Am. (May 2017)