Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

An Image-Inspired Audio Sharpness Index

Abstract : We propose a new non-intrusive (reference-free) objective measure of speech intelligibility that is inspired from previous works on image sharpness. We define the audio Sharpness Index (aSI) as the sensitivity of the spectrogram sparsity to the convolution of the signal with a white noise, and we calculate a closed-form formula of the aSI. Experiments with various speakers, noise and reverberation conditions show a high correlation between the aSI and the well-established Speech Transmission Index (STI), which is intrusive (full-reference). Additionally, the aSI can be used as an intelligibility or clarity criterion to drive sound enhancement algorithms. Experimental results on stereo mixtures of two sounds show that blind source separation based on aSI maximization performs well for speech and for music.
Complete list of metadatas

Cited literature [18 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01528172
Contributor : Lionel Moisan <>
Submitted on : Saturday, May 27, 2017 - 8:07:32 PM
Last modification on : Friday, April 10, 2020 - 5:24:32 PM
Document(s) archivé(s) le : Monday, August 28, 2017 - 5:17:28 PM

File

2017-12.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01528172, version 1

Citation

Gaël Mahé, Lionel Moisan, Mihai Mitrea. An Image-Inspired Audio Sharpness Index. 2017. ⟨hal-01528172⟩

Share

Metrics

Record views

397

Files downloads

309