A robust howling detection algorithm based on a statistical approach

Abstract : This paper presents an algorithm for the detection of howlings that arise in audio signals. Our method is based on the combination of two energy-based features and one new feature related to the frequency stability of a howling component. The decision stage, which implies a Support Vector Machine (SVM) model, outputs a decision every 20 ms. The evaluation, carried out on a large database, showed that the algorithm is able to detect both pure and multiple tones howling in a wide range of energy. Furthermore, even on complex signals such as music, the detection is still efficient with very few false alarms.
Type de document :
Communication dans un congrès
International Workshop on Acoustic Signal Enhancement (IWAENC), Sep 2014, Antibes, France
Liste complète des métadonnées

https://hal.inria.fr/hal-01100273
Contributeur : Pascal Scalart <>
Soumis le : mardi 6 janvier 2015 - 11:13:00
Dernière modification le : mardi 16 janvier 2018 - 15:54:13

Identifiants

  • HAL Id : hal-01100273, version 1

Citation

Joachim Flocon-Cholet, Julien Faure, Alexandre Guérin, Pascal Scalart. A robust howling detection algorithm based on a statistical approach. International Workshop on Acoustic Signal Enhancement (IWAENC), Sep 2014, Antibes, France. 〈hal-01100273〉

Partager

Métriques

Consultations de la notice

647