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.
Type de document :
Pré-publication, Document de travail
MAP5 2017-12. 2017
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-01528172
Contributeur : Lionel Moisan <>
Soumis le : samedi 27 mai 2017 - 20:07:32
Dernière modification le : vendredi 2 juin 2017 - 01:09:18

Fichier

2017-12.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01528172, version 1

Citation

Gaël Mahé, Lionel Moisan, Mihai Mitrea. An Image-Inspired Audio Sharpness Index. MAP5 2017-12. 2017. <hal-01528172>

Partager

Métriques

Consultations de
la notice

56

Téléchargements du document

38