Spectrogram Classification Using Dissimilarity Space
In this work, we combine a Siamese neural network and different clustering techniques to generate a dissimilarity space that is then used to train an SVM for automated animal audio classification. The animal audio datasets used are (i) birds and (ii) cat sounds, which are freely available. We exploi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/12/4176 |
| _version_ | 1797564965965529088 |
|---|---|
| author | Loris Nanni Andrea Rigo Alessandra Lumini Sheryl Brahnam |
| author_facet | Loris Nanni Andrea Rigo Alessandra Lumini Sheryl Brahnam |
| author_sort | Loris Nanni |
| collection | DOAJ |
| description | In this work, we combine a Siamese neural network and different clustering techniques to generate a dissimilarity space that is then used to train an SVM for automated animal audio classification. The animal audio datasets used are (i) birds and (ii) cat sounds, which are freely available. We exploit different clustering methods to reduce the spectrograms in the dataset to a number of centroids that are used to generate the dissimilarity space through the Siamese network. Once computed, we use the dissimilarity space to generate a vector space representation of each pattern, which is then fed into an support vector machine (SVM) to classify a spectrogram by its dissimilarity vector. Our study shows that the proposed approach based on dissimilarity space performs well on both classification problems without ad-hoc optimization of the clustering methods. Moreover, results show that the fusion of CNN-based approaches applied to the animal audio classification problem works better than the stand-alone CNNs. |
| first_indexed | 2024-03-10T19:05:15Z |
| format | Article |
| id | doaj.art-9d41748b36244e26a212cfe23a3e77d0 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T19:05:15Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-9d41748b36244e26a212cfe23a3e77d02023-11-20T04:10:08ZengMDPI AGApplied Sciences2076-34172020-06-011012417610.3390/app10124176Spectrogram Classification Using Dissimilarity SpaceLoris Nanni0Andrea Rigo1Alessandra Lumini2Sheryl Brahnam3DEI, Via Gradenigo 6, 35131 Padova, ItalyDEI, Via Gradenigo 6, 35131 Padova, ItalyDISI, University of Bologna, Via dell’Università 50, 47521 Cesena, ItalyDepartment of Information Technology and Cybersecurity, Missouri State University, 901 S. National Street, Springfield, MO 65804, USAIn this work, we combine a Siamese neural network and different clustering techniques to generate a dissimilarity space that is then used to train an SVM for automated animal audio classification. The animal audio datasets used are (i) birds and (ii) cat sounds, which are freely available. We exploit different clustering methods to reduce the spectrograms in the dataset to a number of centroids that are used to generate the dissimilarity space through the Siamese network. Once computed, we use the dissimilarity space to generate a vector space representation of each pattern, which is then fed into an support vector machine (SVM) to classify a spectrogram by its dissimilarity vector. Our study shows that the proposed approach based on dissimilarity space performs well on both classification problems without ad-hoc optimization of the clustering methods. Moreover, results show that the fusion of CNN-based approaches applied to the animal audio classification problem works better than the stand-alone CNNs.https://www.mdpi.com/2076-3417/10/12/4176audio classificationdissimilarity spacesiamese networkensemble of classifierspattern recognitionanimal audio |
| spellingShingle | Loris Nanni Andrea Rigo Alessandra Lumini Sheryl Brahnam Spectrogram Classification Using Dissimilarity Space Applied Sciences audio classification dissimilarity space siamese network ensemble of classifiers pattern recognition animal audio |
| title | Spectrogram Classification Using Dissimilarity Space |
| title_full | Spectrogram Classification Using Dissimilarity Space |
| title_fullStr | Spectrogram Classification Using Dissimilarity Space |
| title_full_unstemmed | Spectrogram Classification Using Dissimilarity Space |
| title_short | Spectrogram Classification Using Dissimilarity Space |
| title_sort | spectrogram classification using dissimilarity space |
| topic | audio classification dissimilarity space siamese network ensemble of classifiers pattern recognition animal audio |
| url | https://www.mdpi.com/2076-3417/10/12/4176 |
| work_keys_str_mv | AT lorisnanni spectrogramclassificationusingdissimilarityspace AT andrearigo spectrogramclassificationusingdissimilarityspace AT alessandralumini spectrogramclassificationusingdissimilarityspace AT sherylbrahnam spectrogramclassificationusingdissimilarityspace |