Biocoustic Sound Separation Based on FastICA and Infomax Algorithms
In bioacoustics technology, advances such as automated sound recognition based on animal vocalization help in biological research and environmental monitoring. However, in a noisy acoustic environment, where there will be interferences such as overlapping sounds made by multiple species, may greatly hamper the automated sound recognizer performance to identify the specific species. Hence, it is desirable to extract the sound made by the target species from the interferences as a pre-process prior to the recognition to get more accurate results. This paper exploits two Blind Source Separation (BSS) algorithms namely Info-max and FastICA to obtain the target frog sounds from the mixtures. The comparison of algorithm performances is expressed according to Signal-to-Interfere (SIR). The empirical simulation results show that FastICA outperforms Infomax in terms of separation quality.
KeywordsBlind source separation (BSS) FastICA Infomax Frog sound
This work was supported by Universiti Sains Malaysia under Research University (RU) Grant (No:1001.PELECT.8014057).
- 1.Narins, P.M., Feng, A.S.: Hearing and Sound Communication in Amphibians, vol. 28. Springer, New York (2006)Google Scholar
- 2.Obrist, M.K., Pavan, G., Sueur, J., Riede, K., Llusia, D., Márquez, R.: Bioacoustics approaches in biodiversity inventories. Man. F. Rec. Tech. Protoc. All Taxa Biodivers. Invent. 8,68–99 (2010)Google Scholar
- 4.Hyvärinen, A., Karhunen, J., Oja, E.: Independent Component Analysis, Final. Vers. 21(1) (2001)Google Scholar
- 5.Nikam, S., Deosarkar, S.: Fast ICA based technique for non-invasive fetal ECG extraction. In: 2016 Conference on Advances in Signal Processing (CASP), pp. 60–65 (2016)Google Scholar
- 8.Bell, A.J., Sejnowski, T.J.: An information-maximisation approach t o blind separation and blind deconvolution, 1034, pp. 1004–1034 (1995)Google Scholar
- 9.Rutledge, D.N., Bouveresse, J.-R.D.: Independent components analysis with the JADE algorithm. In: TrAC—Trends in Analytical Chemistry, vol. 50, pp. 22–32. Elsevier (2013)Google Scholar