Digital signal processing (2nd ed.): principles, algorithms, and applications
Digital signal processing (2nd ed.): principles, algorithms, and applications
Self-Organizing Maps
Content-Based Classification, Search, and Retrieval of Audio
IEEE MultiMedia
A Study on Content-Based Classification and Retrieval of Audio Database
IDEAS '01 Proceedings of the International Database Engineering & Applications Symposium
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
| Hi-index | 0.00 |
'Soundscapes' are maps that depict the sound content of an area at a time interval. Sound features encapsulate information which can be combined with the visual features of a landscape, in order to produce useful ecological observations/data, for areas of environmental or ecological interest. These include monitoring of the wildlife, the inhabitation and the use/human activities of the area, as they evolve with time. In this paper, a method is proposed for the development of a soundscape - a procedure that requires a hierarchical, coarser-to-finer classification scheme for the environmental sounds. The proposed method is illustrated for echolocation calls produced by different species of bats. Time-frequency representations of the sound signals are obtained as a basis for feature extraction. Vectors of statistical features are classified by an Artificial Neural Network classifier. The experimental results verify the potential of the proposed method for classification of environmental sounds within a soundscape development task.