{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:54:58Z","timestamp":1782316498539,"version":"3.54.5"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T00:00:00Z","timestamp":1763337600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T00:00:00Z","timestamp":1763337600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"DOI":"10.1186\/s13636-025-00426-1","type":"journal-article","created":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T18:27:56Z","timestamp":1763404076000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Advancing guitar emotion recognition through audio data augmentation to enhance smart musical instruments"],"prefix":"10.1186","volume":"2025","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5982-4150","authenticated-orcid":false,"given":"Michele","family":"Rossi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giovanni","family":"Iacca","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Turchet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,17]]},"reference":[{"key":"426_CR1","doi-asserted-by":"publisher","first-page":"8944","DOI":"10.1109\/ACCESS.2018.2876891","volume":"7","author":"L Turchet","year":"2019","unstructured":"L. Turchet, Smart musical instruments: vision, design principles, and future directions. IEEE Access 7, 8944\u20138963 (2019)","journal-title":"IEEE Access"},{"key":"426_CR2","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1007\/s00530-017-0559-4","volume":"24","author":"X Yang","year":"2018","unstructured":"X. Yang, Y. Dong, J. Li, Review of data features-based music emotion recognition methods. Multimed. Syst. 24, 365\u2013389 (2018)","journal-title":"Multimed. Syst."},{"key":"426_CR3","doi-asserted-by":"publisher","first-page":"103340","DOI":"10.1016\/j.ijhcs.2024.103340","volume":"191","author":"L Turchet","year":"2024","unstructured":"L. Turchet, D. Stefani, J. Pauwels, Musician-ai partnership mediated by emotionally-aware smart musical instruments. Int. J. Hum.-Comput. Stud. 191, 103340 (2024)","journal-title":"Int. J. Hum.-Comput. Stud."},{"issue":"7553","key":"426_CR4","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"Y. LeCun, Y. Bengio, G. Hinton, Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"issue":"1","key":"426_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"C. Shorten, T.M. Khoshgoftaar, A survey on image data augmentation for deep learning. J. Big Data 6(1), 1\u201348 (2019)","journal-title":"J. Big Data"},{"key":"426_CR6","doi-asserted-by":"crossref","unstructured":"S.Y. Feng, V. Gangal, J. Wei, S. Chandar, S. Vosoughi, T. Mitamura, E. Hovy. A survey of data augmentation approaches for NLP. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. Association for Computational Linguistics, Online, pp. 968\u2013988 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.84"},{"key":"426_CR7","doi-asserted-by":"crossref","unstructured":"S. Wei, S. Zou, F. Liao et al., in Journal of physics: Conference series. A comparison on data augmentation methods based on deep learning for audio classification, vol. 1453 (IOP Publishing, Bristol, 2020), p. 012085","DOI":"10.1088\/1742-6596\/1453\/1\/012085"},{"issue":"1","key":"426_CR8","first-page":"97","volume":"2","author":"R Mignot","year":"2019","unstructured":"R. Mignot, G. Peeters, An analysis of the effect of data augmentation methods: experiments for a musical genre classification task. Trans. Int Soc. Music. Inf. Retr. 2(1), 97\u2013110 (2019)","journal-title":"Trans. Int Soc. Music. Inf. Retr."},{"key":"426_CR9","doi-asserted-by":"crossref","unstructured":"T. Fukuda, R. Fernandez, A. Rosenberg, S. Thomas, B. Ramabhadran, A. Sorin, G. Kurata, in Interspeech. Data augmentation improves recognition of foreign accented speech (ISCA, Hyderabad, 2018), September, pp. 2409\u20132413","DOI":"10.21437\/Interspeech.2018-1211"},{"issue":"9","key":"426_CR10","doi-asserted-by":"publisher","first-page":"1469","DOI":"10.1109\/TASLP.2015.2438544","volume":"23","author":"X Cui","year":"2015","unstructured":"X. Cui, V. Goel, B. Kingsbury, Data augmentation for deep neural network acoustic modeling. IEEE\/ACM Trans. Audio Speech Lang. Process. 23(9), 1469\u20131477 (2015)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"3","key":"426_CR11","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1109\/LSP.2017.2657381","volume":"24","author":"J Salamon","year":"2017","unstructured":"J. Salamon, J.P. Bello, Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Process. Lett. 24(3), 279\u2013283 (2017)","journal-title":"IEEE Signal Process. Lett."},{"key":"426_CR12","doi-asserted-by":"crossref","unstructured":"N. Davis, K. Suresh, in IEEE Recent Advances in Intelligent Computational Systems). Environmental sound classification using deep convolutional neural networks and data augmentation (IEEE, New York, 2018), pp. 41\u201345","DOI":"10.1109\/RAICS.2018.8635051"},{"key":"426_CR13","doi-asserted-by":"crossref","unstructured":"W. Bian, J. Wang, B. Zhuang, J. Yang, S. Wang, J. Xiao, in Pacific Rim International Conference on Artificial Intelligence. Audio-based music classification with DenseNet and data augmentation (Springer, Cham, 2019), pp. 56\u201365","DOI":"10.1007\/978-3-030-29894-4_5"},{"key":"426_CR14","unstructured":"A. Ramires, X. Serra. Data augmentation for instrument classification robust to audio effects. Proceedings of the 22nd International Conference on Digital Audio Effects (DAFx-19), Birmingham, UK, pp. 1\u20139 (2019)"},{"key":"426_CR15","doi-asserted-by":"publisher","unstructured":"R. Shankar, A.H. Kenfack, A. Somayazulu, A. Venkataraman. A comparative study of data augmentation techniques for deep learning based emotion recognition. arXiv preprint arXiv:2211.05047 (2022). https:\/\/doi.org\/10.48550\/arXiv.2211.05047","DOI":"10.48550\/arXiv.2211.05047"},{"issue":"4","key":"426_CR16","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1109\/TAFFC.2018.2820691","volume":"11","author":"R Panda","year":"2018","unstructured":"R. Panda, R. Malheiro, R.P. Paiva, Novel audio features for music emotion recognition. IEEE Trans. Affect. Comput. 11(4), 614\u2013626 (2018)","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"1","key":"426_CR17","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1109\/TAFFC.2020.3032373","volume":"14","author":"R Panda","year":"2020","unstructured":"R. Panda, R. Malheiro, R.P. Paiva, Audio features for music emotion recognition: a survey. IEEE Trans. Affect. Comput. 14(1), 68\u201388 (2020)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"426_CR18","unstructured":"Y.E. Kim, E.M. Schmidt, R. Migneco, B.G. Morton, P. Richardson, J. Scott et al., in International Society for Music Information Retrieval Conference. Music emotion recognition: A state of the art review, vol. 86 (ISMIR, Utrecth, 2010), pp. 937\u2013952"},{"issue":"6","key":"426_CR19","doi-asserted-by":"publisher","first-page":"166335","DOI":"10.1007\/s11704-021-0569-4","volume":"16","author":"D Han","year":"2022","unstructured":"D. Han, Y. Kong, J. Han, G. Wang, A survey of music emotion recognition. Front. Comput. Sci. 16(6), 166335 (2022)","journal-title":"Front. Comput. Sci."},{"key":"426_CR20","doi-asserted-by":"crossref","unstructured":"X. Jiang, Y. Zhang, G. Lin, L. Yu, Music emotion recognition based on deep learning: A review. IEEE Access 12, 157716\u2013157745 (2024)","DOI":"10.1109\/ACCESS.2024.3484470"},{"issue":"23","key":"426_CR21","doi-asserted-by":"publisher","first-page":"9284","DOI":"10.1016\/j.eswa.2015.08.029","volume":"42","author":"S Deng","year":"2015","unstructured":"S. Deng, D. Wang, X. Li, G. Xu, Exploring user emotion in microblogs for music recommendation. Expert Syst. Appl. 42(23), 9284\u20139293 (2015)","journal-title":"Expert Syst. Appl."},{"key":"426_CR22","doi-asserted-by":"crossref","unstructured":"L. Bunt, M. Pavlicevic, in Music and emotion: Theory and research. Music and emotion: Perspectives from music therapy (Oxford University Press, Oxford, 2001)","DOI":"10.1093\/gmo\/9781561592630.article.19453"},{"key":"426_CR23","doi-asserted-by":"crossref","unstructured":"H. Jalonen, in Federated Conference on Computer Science and Information Systems. Social media and emotions in organisational knowledge creation (IEEE, New York, 2014), pp. 1371\u20131379","DOI":"10.15439\/2014F39"},{"key":"426_CR24","doi-asserted-by":"crossref","unstructured":"M. Huang, W. Rong, T. Arjannikov, N. Jiang, Z. Xiong, in Artificial Neural Networks and Machine Learning. Bi-modal deep Boltzmann machine based musical emotion classification (Springer, Cham, 2016), pp. 199\u2013207","DOI":"10.1007\/978-3-319-44781-0_24"},{"key":"426_CR25","doi-asserted-by":"publisher","unstructured":"X. Liu, Q. Chen, X. Wu, Y. Liu, Y. Liu. CNN based music emotion classification. arXiv preprint arXiv:1704.05665 (2017). https:\/\/doi.org\/10.48550\/arXiv.1704.05665","DOI":"10.48550\/arXiv.1704.05665"},{"issue":"1","key":"426_CR26","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1007\/s11042-019-08192-x","volume":"79","author":"R Sarkar","year":"2020","unstructured":"R. Sarkar, S. Choudhury, S. Dutta, A. Roy, S.K. Saha, Recognition of emotion in music based on deep convolutional neural network. Multimed. Tools Appl. 79(1), 765\u2013783 (2020)","journal-title":"Multimed. Tools Appl."},{"key":"426_CR27","doi-asserted-by":"crossref","unstructured":"P.T. Yang, S.M. Kuang, C.C. Wu, J.L. Hsu, in International Conference on Human-Computer Interaction. Predicting music emotion by using convolutional neural network (Springer, Cham, 2020), pp.\u00a0266\u2013275","DOI":"10.1007\/978-3-030-50341-3_21"},{"issue":"7","key":"426_CR28","doi-asserted-by":"publisher","first-page":"2201","DOI":"10.3390\/s24072201","volume":"24","author":"PL Louro","year":"2024","unstructured":"P.L. Louro, H. Redinho, R. Malheiro, R.P. Paiva, R. Panda, A comparison study of deep learning methodologies for music emotion recognition. Sensors 24(7), 2201 (2024)","journal-title":"Sensors"},{"key":"426_CR29","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1109\/TASLP.2021.3138709","volume":"30","author":"L Turchet","year":"2021","unstructured":"L. Turchet, J. Pauwels, Music emotion recognition: intention of composers-performers versus perception of musicians, non-musicians, and listening machines. IEEE\/ACM Trans. Audio Speech Lang. Process. 30, 305\u2013316 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"426_CR30","doi-asserted-by":"publisher","unstructured":"S. Yang, W. Xiao, M. Zhang, S. Guo, J. Zhao, F. Shen. Image data augmentation for deep learning: A survey. arXiv preprint arXiv:2204.08610 (2022). https:\/\/doi.org\/10.48550\/arXiv.2204.08610","DOI":"10.48550\/arXiv.2204.08610"},{"key":"426_CR31","unstructured":"A. Krizhevsky, I. Sutskever, G.E. Hinton, ImageNet classification with deep convolutional neural networks. In: Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 1. NIPS\u201912, pp. 1097\u20131105."},{"key":"426_CR32","doi-asserted-by":"publisher","unstructured":"S. Grollmisch, E. Cano, Improving semi-supervised learning for audio classification with fixmatch. Electronics 10(15), (2021). https:\/\/doi.org\/10.3390\/electronics10151807","DOI":"10.3390\/electronics10151807"},{"key":"426_CR33","doi-asserted-by":"publisher","unstructured":"D.S. Park, W. Chan, Y. Zhang, C.-C. Chiu, B. Zoph, E.D. Cubuk, Q.V. Le. SpecAugment: a simple data augmentation method for automatic speech recognition. Proceedings of Interspeech 2019, pp. 2613\u20132617 (2019). https:\/\/doi.org\/10.21437\/Interspeech.2019-2680","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"426_CR34","doi-asserted-by":"crossref","unstructured":"J. Wang, S. Kim, Y. Lee, in IEEE International Conference on Acoustics, Speech and Signal Processing. Speech augmentation using wavenet in speech recognition (IEEE, New York, 2019), pp. 6770\u20136774","DOI":"10.1109\/ICASSP.2019.8683388"},{"key":"426_CR35","doi-asserted-by":"publisher","unstructured":"E. Tsunoo, K. Shibata, C. Narisetty, Y. Kashiwagi, S. Watanabe. Data augmentation methods for end-to-end speech recognition on distant-talk scenarios. Proceedings of the 22nd Annual Conference of the International Speech Communication Association (INTERSPEECH 2021), pp. 301\u2013305 (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-958","DOI":"10.21437\/Interspeech.2021-958"},{"key":"426_CR36","unstructured":"N. Jaitly, G.E. Hinton, in ICML Workshop on Deep Learning for Audio, Speech and Language. Vocal tract length perturbation (vtlp) improves speech recognition, vol. 117 (ICML, Atlanta, 2013), p. 21"},{"key":"426_CR37","doi-asserted-by":"crossref","unstructured":"K.J. Piczak, in IEEE International Workshop on Machine Learning for Signal Processing. Environmental sound classification with convolutional neural networks (IEEE, New York, 2015), pp. 1\u20136","DOI":"10.1109\/MLSP.2015.7324337"},{"key":"426_CR38","doi-asserted-by":"crossref","unstructured":"G. Parascandolo, H. Huttunen, T. Virtanen, in IEEE International Conference on Acoustics, Speech and Signal Processing. Recurrent neural networks for polyphonic sound event detection in real life recordings (IEEE, New York, 2016), pp. 6440\u20136444","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"426_CR39","unstructured":"J. Schl\u00fcter, T. Grill, in International Society for Music Information Retrieval Conference. Exploring data augmentation for improved singing voice detection with neural networks (ISMIR, Malaga, 2015)"},{"key":"426_CR40","unstructured":"B. McFee, E.J. Humphrey, J.P. Bello, in International Society for Music Information Retrieval Conference. A software framework for musical data augmentation (ISMIR, Malaga, 2015)"},{"key":"426_CR41","doi-asserted-by":"crossref","unstructured":"R.L. Aguiar, Y.M. Costa, C.N. Silla, in International Joint Conference on Neural Networks. Exploring data augmentation to improve music genre classification with convnets (IEEE, New York, 2018), pp. 1\u20138","DOI":"10.1109\/IJCNN.2018.8489166"},{"key":"426_CR42","doi-asserted-by":"publisher","unstructured":"P. Sobot. Pedalboard. (2021). https:\/\/doi.org\/10.5281\/zenodo.7817838","DOI":"10.5281\/zenodo.7817838"},{"key":"426_CR43","doi-asserted-by":"crossref","unstructured":"B. McFee, C. Raffel, D. Liang, D.P. Ellis, M. McVicar, E. Battenberg, O. Nieto, in Python in Science Conference. librosa: Audio and music signal analysis in Python (SciPy.org, Austin, 2015), pp. 18\u201324","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"426_CR44","doi-asserted-by":"publisher","unstructured":"M. Comunit\u00e0, D. Stowell, J.D. Reiss. Guitar effects recognition and parameter estimation with convolutional neural networks. Journal of the Audio Engineering Society 69(7\/8), 594\u2013604 (2021). https:\/\/doi.org\/10.17743\/jaes.2021.0019","DOI":"10.17743\/jaes.2021.0019"},{"key":"426_CR45","unstructured":"F. Chollet et al. Keras.\u00a0(2015). https:\/\/github.com\/fchollet\/keras"},{"key":"426_CR46","unstructured":"M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen et al., TensorFlow: Large-scale machine learning on heterogeneous systems (2015). https:\/\/www.tensorflow.org\/. Software available from tensorflow.org"},{"key":"426_CR47","unstructured":"J. Pons, O. Nieto, M. Prockup, E.M. Schmidt, A.F. Ehmann, X. Serra. End-to-end learning for music audio tagging at scale. Proceedings of the 19th International Society for Music Information Retrieval Conference (ISMIR 2018), Paris, France, pp. 1\u20139 (2018). International Society for Music Information Retrieval, Canada. ISBN: 978-2-9540351-2-3"},{"key":"426_CR48","unstructured":"D.P. Kingma, J. Ba. Adam: a method for stochastic optimization. Proceedings of the 3rd International Conference for Learning Representations (ICLR) (2015). https:\/\/arxiv.org\/abs\/1412.6980"},{"key":"426_CR49","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel et al., Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"issue":"122","key":"426_CR50","first-page":"16","volume":"19","author":"A Flexer","year":"2007","unstructured":"A. Flexer, A closer look on artist filters for musical genre classification. World 19(122), 16\u201317 (2007)","journal-title":"World"},{"issue":"48","key":"426_CR51","doi-asserted-by":"publisher","first-page":"2173","DOI":"10.21105\/joss.02173","volume":"5","author":"S Herbold","year":"2020","unstructured":"S. Herbold, Autorank: a python package for automated ranking of classifiers. J. Open Source Softw. 5(48), 2173 (2020)","journal-title":"J. Open Source Softw."}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-025-00426-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13636-025-00426-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-025-00426-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T18:28:20Z","timestamp":1763404100000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13636-025-00426-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,17]]},"references-count":51,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["426"],"URL":"https:\/\/doi.org\/10.1186\/s13636-025-00426-1","relation":{},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,17]]},"assertion":[{"value":"5 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"LT is a guest editor for the current special issue: Signal Processing for the Internet of Sounds. All other authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"38"}}