Perceptual and Automatic Evaluations of the Intelligibility of Speech Degraded by Noise Induced Hearing Loss Simulation

  title={Perceptual and Automatic Evaluations of the Intelligibility of Speech Degraded by Noise Induced Hearing Loss Simulation},
  author={Imed Laaridh and Julien Tardieu and Cynthia Magnen and Pascal Gaillard and J{\'e}r{\^o}me Farinas and Julien Pinquier},
This study aims at comparing perceptual and automatic intelligibility measures on degraded speech. It follows a previous study that designed a novel approach for the automatic prediction of Age-Related Hearing Loss (ARHL) effects on speech intelligibility. In this work, we adapted this approach to a different type of hearing disorder: the Noise Induced Hearing Loss (NIHL), i.e., hearing loss caused by noise exposure at work. Thus, we created a speech corpus made of both isolated words and short… 
1 Citations

Figures and Tables from this paper

Advancing an in-memory computing for a multi-accent real-time voice frequency recognition modeling: a comprehensive study of models & mechanism
This study has engrossed on revision and adaptive preparation of auditory models and signifies the auditory understanding of function by which a reflection categorization can be plotted to a system of sub-word divisions.


Automatic Speech Recognition Predicts Speech Intelligibility and Comprehension for Listeners With Simulated Age-Related Hearing Loss.
Both intelligibility and comprehension scores for listeners with simulated ARHL are highly correlated with the performances of an ASR-based system.
Adaptation of the HINT (hearing in noise test) for adult Canadian Francophone populations
The HINT provides an efficient and reliable method of assessing speech intelligibility in quiet and in noise by using an adaptive strategy to measure speech reception thresholds for sentences, thus
Simulation of the effect of threshold elevation and loudness recruitment combined with reduced frequency selectivity on the intelligibility of speech in noise.
Evidence is consistent with previous evidence indicating that only part of the decrease of performance produced by actual cochlear hearing loss can be compensated by conventional linear hearing aids.
Effects of presentation mode and repeated familiarization on intelligibility of dysarthric speech.
It was revealed that audiovisual information did not enhance intelligibility relative to audio-only information for 4 of the 5 speakers studied, and the one speaker whose intelligibility increased when audiovISual information was presented had the most severe dysarthria and concomitant motor impairments.
Perceptual linear predictive (PLP) analysis of speech.
  • H. Hermansky
  • Physics
    The Journal of the Acoustical Society of America
  • 1990
A new technique for the analysis of speech, the perceptual linear predictive (PLP) technique, which uses three concepts from the psychophysics of hearing to derive an estimate of the auditory spectrum, and yields a low-dimensional representation of speech.
Audiometric notch as a sign of noise induced hearing loss.
To diagnose NIHL it is important to elicit a detailed and accurate history of exposure to noise: although the notch at 4 kHz is a well established clinical sign and may be valuable in confirming the diagnosis, the 6 kHz notch is variable and of limited importance.
Speaker normalization on conversational telephone speech
A new system for warp scale selection which uses a simple generic voiced speech model to rapidly select appropriate frequency scales and is sufficiently streamlined that it can moved completely into the front-end processing.
The LIUM speech transcription system: a CMU Sphinx III-based system for French broadcast news
This paper presents the system used by the LIUM to participate in ESTER, the french broadcast news evaluation campaign, based on the CMU Sphinx 3.3 (fast) decoder, with very few modifications and a simple MAP acoustic model estimation.
Factors Influencing Help Seeking, Hearing Aid Uptake, Hearing Aid Use and Satisfaction With Hearing Aids: A Review of the Literature
The vast majority of studies showed no relationship of age and gender with any of the outcome domains, and there was only one factor positively affecting all four outcome variables.
The 1997 CMU Sphinx-3 English Broadcast News Transcription System
This paper describes the 1997 Hub-4 Broadcast News Sphinx3 speech recognition system. This year’s system includes fullbandwidth acoustic models trained on Broadcast News and Wall Street Journal