Similarity-Based Summarization of Music Files for Support Vector Machines
Automatic retrieval of music information is an active area of research in which problems such as automatically assigning genres or descriptors of emotional content to music emerge. Recent advancements in the area rely on the use of deep learning, which allows researchers to operate on a low-level de...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2018-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2018/1935938 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832548932253646848 |
|---|---|
| author | Jan Jakubik Halina Kwaśnicka |
| author_facet | Jan Jakubik Halina Kwaśnicka |
| author_sort | Jan Jakubik |
| collection | DOAJ |
| description | Automatic retrieval of music information is an active area of research in which problems such as automatically assigning genres or descriptors of emotional content to music emerge. Recent advancements in the area rely on the use of deep learning, which allows researchers to operate on a low-level description of the music. Deep neural network architectures can learn to build feature representations that summarize music files from data itself, rather than expert knowledge. In this paper, a novel approach to applying feature learning in combination with support vector machines to musical data is presented. A spectrogram of the music file, which is too complex to be processed by SVM, is first reduced to a compact representation by a recurrent neural network. An adjustment to loss function of the network is proposed so that the network learns to build a representation space that replicates a certain notion of similarity between annotations, rather than to explicitly make predictions. We evaluate the approach on five datasets, focusing on emotion recognition and complementing it with genre classification. In experiments, the proposed loss function adjustment is shown to improve results in classification and regression tasks, but only when the learned similarity notion corresponds to a kernel function employed within the SVM. These results suggest that adjusting deep learning methods to build data representations that target a specific classifier or regressor can open up new perspectives for the use of standard machine learning methods in music domain. |
| format | Article |
| id | doaj-art-0535e7bb379f4082b0870c0faae6f41c |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2018-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-0535e7bb379f4082b0870c0faae6f41c2025-02-03T06:12:36ZengWileyComplexity1076-27871099-05262018-01-01201810.1155/2018/19359381935938Similarity-Based Summarization of Music Files for Support Vector MachinesJan Jakubik0Halina Kwaśnicka1Department of Computational Intelligence, Faculty of Computer Science and Management, Wrocław University of Science and Technology, Wrocław, PolandDepartment of Computational Intelligence, Faculty of Computer Science and Management, Wrocław University of Science and Technology, Wrocław, PolandAutomatic retrieval of music information is an active area of research in which problems such as automatically assigning genres or descriptors of emotional content to music emerge. Recent advancements in the area rely on the use of deep learning, which allows researchers to operate on a low-level description of the music. Deep neural network architectures can learn to build feature representations that summarize music files from data itself, rather than expert knowledge. In this paper, a novel approach to applying feature learning in combination with support vector machines to musical data is presented. A spectrogram of the music file, which is too complex to be processed by SVM, is first reduced to a compact representation by a recurrent neural network. An adjustment to loss function of the network is proposed so that the network learns to build a representation space that replicates a certain notion of similarity between annotations, rather than to explicitly make predictions. We evaluate the approach on five datasets, focusing on emotion recognition and complementing it with genre classification. In experiments, the proposed loss function adjustment is shown to improve results in classification and regression tasks, but only when the learned similarity notion corresponds to a kernel function employed within the SVM. These results suggest that adjusting deep learning methods to build data representations that target a specific classifier or regressor can open up new perspectives for the use of standard machine learning methods in music domain.http://dx.doi.org/10.1155/2018/1935938 |
| spellingShingle | Jan Jakubik Halina Kwaśnicka Similarity-Based Summarization of Music Files for Support Vector Machines Complexity |
| title | Similarity-Based Summarization of Music Files for Support Vector Machines |
| title_full | Similarity-Based Summarization of Music Files for Support Vector Machines |
| title_fullStr | Similarity-Based Summarization of Music Files for Support Vector Machines |
| title_full_unstemmed | Similarity-Based Summarization of Music Files for Support Vector Machines |
| title_short | Similarity-Based Summarization of Music Files for Support Vector Machines |
| title_sort | similarity based summarization of music files for support vector machines |
| url | http://dx.doi.org/10.1155/2018/1935938 |
| work_keys_str_mv | AT janjakubik similaritybasedsummarizationofmusicfilesforsupportvectormachines AT halinakwasnicka similaritybasedsummarizationofmusicfilesforsupportvectormachines |