Data-Driven Audio Feature Space Clustering for Automatic Sound Recognition in Radio Broadcast News
Authors:
Open Access
- 12 April 2017
- journal article
- research article
- Published by World Scientific Pub Co Pte Ltd in International Journal on Artificial Intelligence Tools
- Vol. 26 (02)
Abstract
Aiming to an automatic sound recognizer for radio broadcasting events, a methodology of clustering the audio feature space using the discrimination ability of the audio descriptors as a criterion, is investigated in this work. From a given and close set of audio events, commonly found in broadcast news transmissions, a large set of audio descriptors is extracted and their data-driven ranking of relevance is clustered, providing a more robust feature selection. The clusters of the feature space are feeding machine learning algorithms implemented as classification models during the experimental evaluation. This methodology showed that support vector machines provide significantly good results, considering the achieved accuracy due to their ability of coping well in high dimensionality experimental conditions.Keywords
This publication has 17 references indexed in Scilit:
- Context-adaptive pre-processing scheme for robust speech recognition in fast-varying noise environmentSignal Processing, 2011
- Discrimination of speech from nonspeeech in broadcast news based on modulation frequency featuresSpeech Communication, 2011
- Sound Event Recognition With Probabilistic Distance SVMsIEEE Transactions on Audio, Speech, and Language Processing, 2010
- Speaker segmentation and clusteringSignal Processing, 2008
- Detection of Cough Signals in Continuous Audio Recordings Using Hidden Markov ModelsIEEE Transactions on Biomedical Engineering, 2006
- Audio thumbnailing of popular music using chroma-based representationsIEEE Transactions on Multimedia, 2005
- Audio Classification Based on MPEG-7 Spectral Basis RepresentationsIEEE Transactions on Circuits and Systems for Video Technology, 2004
- Content-based audio classification and retrieval using a fuzzy logic system: towards multimedia search enginesSoft Computing, 2002
- Improvements to Platt's SMO Algorithm for SVM Classifier DesignNeural Computation, 2001
- Instance-based learning algorithmsMachine Learning, 1991