Non-speech environmental sound identification for surveillance using self-organizing-maps

Authors:
Renate Sitte;Liam Willets
Affiliations:
School of Information and Communication Technology Griffith University, Queensland, Australia;School of Information and Communication Technology Griffith University, Queensland, Australia
Venue:
SPPR'07 Proceedings of the Fourth conference on IASTED International Conference: Signal Processing, Pattern Recognition, and Applications
Year:
2007

Citing 4
Cited 0

Self-organization and associative memory: 3rd edition

Self-organization and associative memory: 3rd edition
Speaker-independent recognition of isolated words using clustering techniques

Readings in speech recognition
Comparison of techniques for environmental sound recognition

Pattern Recognition Letters
Information extraction from sound for medical telemonitoring

IEEE Transactions on Information Technology in Biomedicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present a new approach for nonspeech sound identification using Self Organizing Maps (SOM). We have found that by applying the SOM identification in a two-staged process, the identification rate surpasses the performance of other identification attempts. We have experimented with up to sixty different sounds maintaining a success rate of 70%. While even higher ratess have been reported by others, such high rates were typically limited to less than ten different sounds. We also found that as little as four sound-samples from each sound are sufficient for training the SOM. Nonspeech environmental sound identification is different from speaker and music instrument identification in that it spans (in theory) an unbounded range of frequencies. This makes the pool of sound patterns almost limitless and consequently the pattern matching quite extensive and difficult.