A mixture model-based real-time audio sources classification method

Baelde, Maxime; Biernacki, Christophe; Greff, Raphaël

Type de document :

Autre communication scientifique (congrès sans actes - poster - séminaire...): Communication dans un congrès avec actes

Titre :

A mixture model-based real-time audio sources classification method

Auteur(s) :

Baelde, Maxime [Auteur]
Laboratoire Paul Painlevé - UMR 8524 [LPP]
MOdel for Data Analysis and Learning [MODAL]
A-Volute [Roubaix]
Biernacki, Christophe [Auteur]
Laboratoire Paul Painlevé - UMR 8524 [LPP]
MOdel for Data Analysis and Learning [MODAL]
Greff, Raphaël [Auteur]
A-Volute [Roubaix]

Titre de la manifestation scientifique :

The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP2017

Ville :

New Orleans

Pays :

Etats-Unis d'Amérique

Date de début de la manifestation scientifique :

2017-03-05

Mot(s)-clé(s) en anglais :

real-time
audio identification
statistical
learning
mixture models
sound classification
machine learn-

Discipline(s) HAL :

Statistiques [stat]/Méthodologie [stat.ME]

Résumé en anglais : [en]

Recent research on machine learning focuses on audio source identification in complex environments. They rely on extracting features from audio signals and use machine learning techniques to model the sound classes. However, ...
Lire la suite >Recent research on machine learning focuses on audio source identification in complex environments. They rely on extracting features from audio signals and use machine learning techniques to model the sound classes. However, such techniques are often not optimized for a real-time implementation and in multi-source conditions. We propose a new real-time audio single-source classification method based on a dictionary of sound models (that can be extended to a multi-source setting). The sound spectrums are modeled with mixture models and form a dictionary. The classification is based on a comparison with all the elements of the dictionary by computing likelihoods and the best match is used as a result. We found that this technique outperforms classic methods within a temporal horizon of 0.5s per decision (achieved 6% of errors on a database composed of 50 classes). Future works will focus on the multi-sources classification and reduce the computational load.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

Laboratoire Paul Painlevé - UMR 8524

Source :

Harvested from HAL

Fichiers

document
Accès libre
Accéder au document

baelde.pdf
Accès libre
Accéder au document

A mixture model-based real-time audio ... BibTeX CSV Excel RIS

Fichiers

A mixture model-based real-time audio ...

BibTeX

CSV

Excel

RIS