Robust Speech Music Discrimination Using Spectrum's First Order Statistics and Neural Networks

Abstract : Most of speech/music discrimination techniques proposed in the literature need a great amount of training data in order to provide acceptable results. Besides, they are usually context-dependent. In this paper, we propose a novel technique for speech/music discrimination which relies on first order sound spectrum's statistics as feature vector and a neural network for classification. Experiments driven on 20000 seconds of various audio data show that the proposed technique has a great ability of generalization since a classification accuracy of 96% has been achieved only after a training phase on 80 seconds audio data. Furthermore, the proposed technique is context-independent as it can be applied to various audio sources.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01587101
Contributor : Équipe Gestionnaire Des Publications Si Liris <>
Submitted on : Wednesday, September 13, 2017 - 4:23:32 PM
Last modification on : Thursday, November 21, 2019 - 2:21:13 AM

Identifiers

Citation

Hadi Harb, Liming Chen. Robust Speech Music Discrimination Using Spectrum's First Order Statistics and Neural Networks. International Symposium on Signal Processing and its Applications, ISSPA 2003, Jul 2003, Paris, France. ⟨10.1109/ISSPA.2003.1224831⟩. ⟨hal-01587101⟩

Share

Metrics

Record views

77