Improving intelligibility prediction under informational masking using an auditory saliency model

Tang, Y; Cox, TJ

Abstract

The reduction of speech intelligibility in noise is usually dominated by energetic masking (EM) and informational masking (IM).
Most state-of-the-art objective intelligibility measures (OIM) estimate intelligibility by quantifying EM. Few measures model the
effect of IM in detail. In this study, an auditory saliency model,
which intends to measure the probability of the sources obtaining auditory attention in a bottom-up process, was integrated into
an OIM for improving the performance of intelligibility prediction under IM. While EM is accounted for by the original OIM,
IM is assumed to arise from the listener’s attention switching between the target and competing sounds existing in the auditory
scene. The performance of the proposed method was evaluated
along with three reference OIMs by comparing the model predictions to the listener word recognition rates, for different noise
maskers, some of which introduce IM. The results shows that the
predictive accuracy of the proposed method is as good as the best
reported in the literature. The proposed method, however, provides a physiologically-plausible possibility for both IM and EM
modelling.

Citation

Tang, Y., & Cox, T. (2018, September). Improving intelligibility prediction under informational masking using an auditory saliency model. Presented at International Conference on Digital Audio Effects, Aveiro, Portugal

• Presentation Conference Type: Speech
• Conference Name: International Conference on Digital Audio Effects
• Conference Location: Aveiro, Portugal
• Start Date: Sep 4, 2018
• End Date: Sep 8, 2018
• Acceptance Date: May 25, 2018
• Publication Date: Sep 4, 2018
• Deposit Date: May 25, 2018
• Publicly Available Date: Sep 9, 2018
• Publisher URL: http://dafx2018.web.ua.pt/index.html
• Additional Information: Event Type : Conference