Acoustic Classification of Cat Breed Based on Time and Frequency Domain Features
The emerging field of Bioacoustics has been presenting significant research activity lately, and thanks to the use of machine learning methods, several tools and methodologies have been established for identifying certain patterns and meanings in animal vocalizations. Animal sounds can vary over tim...
Guardado en:
Autores principales: | , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
FRUCT
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/5c42e9fd449440309ea27d40453d0d35 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:5c42e9fd449440309ea27d40453d0d35 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:5c42e9fd449440309ea27d40453d0d352021-11-20T15:59:33ZAcoustic Classification of Cat Breed Based on Time and Frequency Domain Features2305-72542343-073710.23919/FRUCT53335.2021.9599975https://doaj.org/article/5c42e9fd449440309ea27d40453d0d352021-10-01T00:00:00Zhttps://www.fruct.org/publications/fruct30/files/Rac.pdfhttps://doaj.org/toc/2305-7254https://doaj.org/toc/2343-0737The emerging field of Bioacoustics has been presenting significant research activity lately, and thanks to the use of machine learning methods, several tools and methodologies have been established for identifying certain patterns and meanings in animal vocalizations. Animal sounds can vary over time in intensity and patterns produced between different breeds of the same species, both for physiological reasons and for different emotional states and needs. Pets, such as dogs and cats, are no exception, thus allowing a vocal distinction between breeds. This article studies classification of the cat breed, in particular on the Maine Coon and European Shorthair breed, based on the public audio dataset CatMeows. To this end, we employed features coming from time and frequency domain capturing relevant information as regard to the present audio structure. Subsequently, audio pattern recognition was carried out by means of k-means clustering, k-NN, and multilayer perceptron learning models. After extensive experiments, we obtained very promising results , with an average accuracy that runs around 98%. In particular, time-domain features presented a strong contribution, as demonstrated by the results using k-means.William RaccagniStavros NtalampirasFRUCTarticleaudio classificationcat breedbioacousticsanimal vocalizationscat vocalizationsTelecommunicationTK5101-6720ENProceedings of the XXth Conference of Open Innovations Association FRUCT, Vol 30, Iss 1, Pp 184-189 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
audio classification cat breed bioacoustics animal vocalizations cat vocalizations Telecommunication TK5101-6720 |
spellingShingle |
audio classification cat breed bioacoustics animal vocalizations cat vocalizations Telecommunication TK5101-6720 William Raccagni Stavros Ntalampiras Acoustic Classification of Cat Breed Based on Time and Frequency Domain Features |
description |
The emerging field of Bioacoustics has been presenting significant research activity lately, and thanks to the use of machine learning methods, several tools and methodologies have been established for identifying certain patterns and meanings in animal vocalizations. Animal sounds can vary over time in intensity and patterns produced between different breeds of the same species, both for physiological reasons and for different emotional states and needs. Pets, such as dogs and cats, are no exception, thus allowing a vocal distinction between breeds. This article studies classification of the cat breed, in particular on the Maine Coon and European Shorthair breed, based on the public audio dataset CatMeows. To this end, we employed features coming from time and frequency domain capturing relevant information as regard to the present audio structure. Subsequently, audio pattern recognition was carried out by means of k-means clustering, k-NN, and multilayer perceptron learning models. After extensive experiments, we obtained very promising results , with an average accuracy that runs around 98%. In particular, time-domain features presented a strong contribution, as demonstrated by the results using k-means. |
format |
article |
author |
William Raccagni Stavros Ntalampiras |
author_facet |
William Raccagni Stavros Ntalampiras |
author_sort |
William Raccagni |
title |
Acoustic Classification of Cat Breed Based on Time and Frequency Domain Features |
title_short |
Acoustic Classification of Cat Breed Based on Time and Frequency Domain Features |
title_full |
Acoustic Classification of Cat Breed Based on Time and Frequency Domain Features |
title_fullStr |
Acoustic Classification of Cat Breed Based on Time and Frequency Domain Features |
title_full_unstemmed |
Acoustic Classification of Cat Breed Based on Time and Frequency Domain Features |
title_sort |
acoustic classification of cat breed based on time and frequency domain features |
publisher |
FRUCT |
publishDate |
2021 |
url |
https://doaj.org/article/5c42e9fd449440309ea27d40453d0d35 |
work_keys_str_mv |
AT williamraccagni acousticclassificationofcatbreedbasedontimeandfrequencydomainfeatures AT stavrosntalampiras acousticclassificationofcatbreedbasedontimeandfrequencydomainfeatures |
_version_ |
1718419426821275648 |