Document Detail

An efficient code for environmental sound classification.
MedLine Citation:
PMID:  19354684     Owner:  NLM     Status:  In-Data-Review    
Much work has been devoted in recent years to the goal of developing an automated sound recognition system that can accurately and efficiently classify a wide variety of common environmental sounds according to their generating source. The effort is driven, in part, by the desire to understand our own ability to reconstruct from sound an accurate perception of everyday objects and events present in our natural environment [cf. A. S. Bregman, Auditory Scene Analysis, MIT Press (1990)]. Here an efficient code is described for classifying environmental sounds that exploits a recent significant advance in sparse signal reconstruction known as compressed sensing (CS) [cf. D. L. Donoho, IEEE Trans. Inf. Theory, 52, 1289-1306 (2006)]. CS involves a novel approach to sampling in which the salient information in signals is recovered from the projection onto a small set of random basis functions. The advantage of CS over traditional Fourier or wavelet representations is its capacity to allow accurate classification at low signal-to-noise ratios based on few samples and little or no prior information about signals. To demonstrate we compare CS-based and Fourier-based classification for several representative environmental sound classification tasks. [Work supported by NIDCD].
Robert Lutfi; Raman Arora; Ching-Ju Liu
Related Documents :
10947254 - Feature selection and classifier performance in computer-aided diagnosis: the effect of...
20879324 - Hippocampal shape classification using redundancy constrained feature selection.
21878144 - Multipoint maximum likelihood mapping in a full-sib family of an outbreeding species.
19324604 - Optimisation and data mining techniques for the screening of epileptic patients.
17020624 - High fidelity medical simulation in the difficult environment of a helicopter: feasibil...
21487784 - Model learning for robot control: a survey.
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  The Journal of the Acoustical Society of America     Volume:  125     ISSN:  1520-8524     ISO Abbreviation:  J. Acoust. Soc. Am.     Publication Date:  2009 Apr 
Date Detail:
Created Date:  2009-04-09     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  7503051     Medline TA:  J Acoust Soc Am     Country:  United States    
Other Details:
Languages:  eng     Pagination:  2528     Citation Subset:  IM    
Dept. of Communicative Disord., Univ. of Wisconsin, Madison, WI 53706, ralutfi@wisc.eduUniv. of Wisconsin, Madison, WI 53706,
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  A computational model for auditory saliency of environmental sound.
Next Document:  Matching the waveform and the temporal window in stimulus generation.