Histogram of gradients of Time-Frequency Representations for Audio Scene Detection
Authors:
Open Access
- 2 December 2014
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 23 (23299290) , 1
Abstract
Presents our entry to the Detection and Classification of Acoustic Scenes challenge. The approach we propose for classifying acoustic scenes is based on transforming the audio signal into a time-frequency representation and then in extracting relevant features about shapes and evolutions of time-frequency structures. These features are based on histogram of gradients that are subsequently fed to a multi-class linear support vector machines.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Large-scale audio feature extraction and SVM for acoustic scene classification2013
- T-HOG: An effective gradient-based descriptor for single line text regionsPattern Recognition, 2013
- A call-independent and automatic acoustic system for the individual recognition of animals: A novel model using four passerinesPattern Recognition, 2010
- Feature extracted from wavelet decomposition using biorthogonal Riesz basis for text-independent speaker recognitionPattern Recognition, 2008
- The bag-of-frames approach to audio pattern recognition: A sufficient model for urban soundscapes but not for polyphonic musicThe Journal of the Acoustical Society of America, 2007
- Acoustic environment classificationACM Transactions on Speech and Language Processing, 2006
- Efficient wavelet adaptation for hybrid wavelet–large margin classifiersPattern Recognition, 2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Comparison of techniques for environmental sound recognitionPattern Recognition Letters, 2003
- Calculation of a constant Q spectral transformThe Journal of the Acoustical Society of America, 1991