A mixture model-based real-time audio ...
Document type :
Autre communication scientifique (congrès sans actes - poster - séminaire...): Communication dans un congrès avec actes
Title :
A mixture model-based real-time audio sources classification method
Author(s) :
Baelde, Maxime [Auteur]
A-Volute [Roubaix]
MOdel for Data Analysis and Learning [MODAL]
Laboratoire Paul Painlevé - UMR 8524 [LPP]
Biernacki, Christophe [Auteur]
MOdel for Data Analysis and Learning [MODAL]
Laboratoire Paul Painlevé - UMR 8524 [LPP]
Greff, Raphaël [Auteur]
A-Volute [Roubaix]
A-Volute [Roubaix]
MOdel for Data Analysis and Learning [MODAL]
Laboratoire Paul Painlevé - UMR 8524 [LPP]
Biernacki, Christophe [Auteur]
MOdel for Data Analysis and Learning [MODAL]
Laboratoire Paul Painlevé - UMR 8524 [LPP]
Greff, Raphaël [Auteur]
A-Volute [Roubaix]
Conference title :
The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP2017
City :
New Orleans
Country :
Etats-Unis d'Amérique
Start date of the conference :
2017-03-05
English keyword(s) :
real-time
audio identification
statistical
learning
mixture models
sound classification
machine learn-
audio identification
statistical
learning
mixture models
sound classification
machine learn-
HAL domain(s) :
Statistiques [stat]/Méthodologie [stat.ME]
English abstract : [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, ...
Show more >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.Show less >
Show more >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.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- document
- Open access
- Access the document
- baelde.pdf
- Open access
- Access the document