A Bag-of-Features approach to acoustic event detection
Authors:
- 1 May 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 401 (15206149) , 3704-3708
Abstract
The classification of acoustic events in indoor environments is an important task for many practical applications in smart environments. In this paper a novel approach for classifying acoustic events that is based on a Bag-of-Features approach is proposed. Mel and gammatone frequency cepstral coefficients that originate from psychoacoustic models are used as input features for the Bag-of representation. Rather than using a prior classification or segmentation step to eliminate silence and background noise, Bag-of-Features representations are learned for a background class. Supervised learning of codebooks and temporal coding are shown to improve the recognition rates. Three different databases are used for the experiments: the CLEAR sound event dataset, the D-CASE event dataset and a new set of smart room recordings.Keywords
This publication has 16 references indexed in Scilit:
- Partially Supervised Speaker ClusteringIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- The devil is in the details: an evaluation of recent feature encoding methods2011
- Machine Hearing: An Emerging Field [Exploratory DSPIEEE Signal Processing Magazine, 2010
- Supervised Learning of Quantizer Codebooks by Information Loss MinimizationIEEE Transactions on Pattern Analysis and Machine Intelligence, 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
- CLEAR Evaluation of Acoustic Event Detection and Classification Systems2007
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories2006
- Automatic analysis of multimodal group actions in meetingsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- Learning the parts of objects by non-negative matrix factorizationNature, 1999
- A method of signal extraction from noisy signal based on auditory scene analysisSpeech Communication, 1999