Utilize este identificador para referenciar este registo:
https://hdl.handle.net/10316/94071
Título: | Novel Audio Features for Music Emotion Recognition | Autor: | Panda, Renato Malheiro, Ricardo Paiva, Rui Pedro |
Palavras-chave: | Affective computing; Audio databases; Emotion recognition; Feature extraction; Music information retrieval | Data: | 2020 | Editora: | IEEE | Projeto: | info:eu-repo/grantAgreement/FCT/5876-PPCDTI/102185/PT/MOODetector - A System for Mood-based Classification and Retrieval of Audio Music info:eu-repo/grantAgreement/FCT/SFRH/SFRH/BD/91523/2012/PT/EMOTION-BASED ANALYSIS AND CLASSIFICATION OF AUDIO MUSIC |
Volume: | 11 | Número: | 4 | Resumo: | This work advances the music emotion recognition state-of-the-art by proposing novel emotionally-relevant audio features. We reviewed the existing audio features implemented in well-known frameworks and their relationships with the eight commonly defined musical concepts. This knowledge helped uncover musical concepts lacking computational extractors, to which we propose algorithms - namely related with musical texture and expressive techniques. To evaluate our work, we created a public dataset of 900 audio clips, with subjective annotations following Russell's emotion quadrants. The existent audio features (baseline) and the proposed features (novel) were tested using 20 repetitions of 10-fold cross-validation. Adding the proposed features improved the F1-score to 76.4 percent (by 9 percent), when compared to a similar number of baseline-only features. Moreover, analysing the features relevance and results uncovered interesting relations, namely the weight of specific features and musical concepts to each emotion quadrant, and warrant promising new directions for future research in the field of music emotion recognition, interactive media, and novel music interfaces. | URI: | https://hdl.handle.net/10316/94071 | ISSN: | 1949-3045 2371-9850 |
DOI: | 10.1109/TAFFC.2018.2820691 | Direitos: | embargoedAccess |
Aparece nas coleções: | I&D CISUC - Artigos em Revistas Internacionais |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
Panda, Malheiro, Paiva - 2020 - Novel Audio Features for Music Emotion Recognition.pdf | IEEE Proof (non-final) | 1.92 MB | Adobe PDF | Ver/Abrir |
Citações SCOPUSTM
95
Visto em 14/out/2024
Citações WEB OF SCIENCETM
82
Visto em 2/out/2024
Visualizações de página
292
Visto em 15/out/2024
Downloads
1.072
Visto em 15/out/2024
Google ScholarTM
Verificar
Altmetric
Altmetric
Este registo está protegido por Licença Creative Commons