{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T15:01:34Z","timestamp":1742914894675,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031441974"},{"type":"electronic","value":"9783031441981"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-44198-1_11","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T08:02:34Z","timestamp":1695283354000},"page":"124-136","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Boost Predominant Instrument Recognition Performance with\u00a0MagiaSearch and\u00a0MagiaClassifier"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1051-1862","authenticated-orcid":false,"given":"Hao","family":"Zhou","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2713-0348","authenticated-orcid":false,"given":"Zhen","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3597-939X","authenticated-orcid":false,"given":"Shusong","family":"Xing","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8110-9944","authenticated-orcid":false,"given":"Zujun","family":"Gu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4554-2351","authenticated-orcid":false,"given":"Binhui","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"unstructured":"Bosch, J.J., Janer, J., Fuhrmann, F., Herrera, P.: A comparison of sound segregation techniques for predominant instrument recognition in musical audio signals. In: ISMIR, pp. 559\u2013564 (2012)","key":"11_CR1"},{"issue":"2","key":"11_CR2","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1109\/TSMCB.2007.913394","volume":"38","author":"JD Deng","year":"2008","unstructured":"Deng, J.D., Simmermacher, C., Cranefield, S.: A study on feature analysis for musical instrument classification. IEEE Trans. Syst. Man Cybern. Part B (Cybern.) 38(2), 429\u2013438 (2008)","journal-title":"IEEE Trans. Syst. Man Cybern. Part B (Cybern.)"},{"doi-asserted-by":"crossref","unstructured":"Eronen, A.: Comparison of features for musical instrument recognition. In: Proceedings of the 2001 IEEE Workshop on the Applications of Signal Processing to Audio and Acoustics (Cat. No. 01TH8575), pp. 19\u201322. IEEE (2001)","key":"11_CR3","DOI":"10.1109\/ASPAA.2001.969532"},{"doi-asserted-by":"crossref","unstructured":"Fanelli, A.M., Caponetti, L., Castellano, G., Buscicchio, C.A.: Content-based recognition of musical instruments. In: Proceedings of the Fourth IEEE International Symposium on Signal Processing and Information Technology, pp. 361\u2013364. IEEE (2004)","key":"11_CR4","DOI":"10.1109\/ISSPIT.2004.1433794"},{"doi-asserted-by":"crossref","unstructured":"Gaido, M., Gangi, M.A.D., Negri, M., Turchi, M.: End-to-end speech-translation with knowledge distillation: Fbk@iwslt2020. In: Proceedings of the 17th International Conference on Spoken Language Translation, IWSLT 2020, Online, 9\u201310 July 2020, pp. 80\u201388. Association for Computational Linguistics (2020)","key":"11_CR5","DOI":"10.18653\/v1\/2020.iwslt-1.8"},{"doi-asserted-by":"crossref","unstructured":"Gong, Y., Chung, Y.A., Glass, J.: AST: audio spectrogram transformer. In: Proceedings of the Interspeech 2021, pp. 571\u2013575 (2021)","key":"11_CR6","DOI":"10.21437\/Interspeech.2021-698"},{"unstructured":"Gururani, S., Sharma, M., Lerch, A.: An attention mechanism for musical instrument recognition. In: Proceedings of the 20th International Society for Music Information Retrieval Conference, ISMIR 2019, Delft, The Netherlands, 4\u20138 November 2019, pp. 83\u201390 (2019)","key":"11_CR7"},{"doi-asserted-by":"crossref","unstructured":"Hidaka, S., Wakamiya, K., Kaburagi, T.: An investigation of the effectiveness of phase for audio classification. In: 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2022, pp. 3708\u20133712. IEEE (2022)","key":"11_CR8","DOI":"10.1109\/ICASSP43922.2022.9746037"},{"doi-asserted-by":"crossref","unstructured":"Hung, Y.N., Chen, Y.A., Yang, Y.H.: Multitask learning for frame-level instrument recognition. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2019, pp. 381\u2013385. IEEE (2019)","key":"11_CR9","DOI":"10.1109\/ICASSP.2019.8683426"},{"unstructured":"Hwang, Y., Cho, H., Yang, H., Won, D.O., Oh, I., Lee, S.W.: Mel-spectrogram augmentation for sequence to sequence voice conversion. arXiv preprint arXiv:2001.01401 (2020)","key":"11_CR10"},{"doi-asserted-by":"crossref","unstructured":"Li, X., Zhang, Y., Zhuang, X., Liu, D.: Frame-level SpecAugment for deep convolutional neural networks in hybrid ASR systems. In: 2021 IEEE Spoken Language Technology Workshop (SLT), pp. 209\u2013214. IEEE (2021)","key":"11_CR11","DOI":"10.1109\/SLT48900.2021.9383626"},{"doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer V2: scaling up capacity and resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12009\u201312019 (2022)","key":"11_CR12","DOI":"10.1109\/CVPR52688.2022.01170"},{"unstructured":"Marques, J., Moreno, P.J.: A study of musical instrument classification using Gaussian mixture models and support vector machines. Cambridge Research Laboratory Technical Report Series CRL 4, 143 (1999)","key":"11_CR13"},{"issue":"3","key":"11_CR14","doi-asserted-by":"publisher","first-page":"1768","DOI":"10.1121\/1.424083","volume":"104","author":"KD Martin","year":"1998","unstructured":"Martin, K.D., Kim, Y.E.: Musical instrument identification: a pattern-recognition approach. J. Acoust. Soc. Am. 104(3), 1768 (1998)","journal-title":"J. Acoust. Soc. Am."},{"unstructured":"Martin, K.D.: Sound-source recognition: a theory and computational model. Ph.D. thesis, Massachusetts Institute of Technology (1999)","key":"11_CR15"},{"doi-asserted-by":"crossref","unstructured":"Park, D.S., et al.: SpecAugment: a simple data augmentation method for automatic speech recognition. In: Proceedings of the Interspeech 2019, pp. 2613\u20132617 (2019)","key":"11_CR16","DOI":"10.21437\/Interspeech.2019-2680"},{"doi-asserted-by":"crossref","unstructured":"Racharla, K., Kumar, V., Jayant, C.B., Khairkar, A., Harish, P.: Predominant musical instrument classification based on spectral features. In: 2020 7th International Conference on Signal Processing and Integrated Networks (SPIN), pp. 617\u2013622. IEEE (2020)","key":"11_CR17","DOI":"10.1109\/SPIN48934.2020.9071125"},{"doi-asserted-by":"crossref","unstructured":"Saeed, A., Grangier, D., Zeghidour, N.: Contrastive learning of general-purpose audio representations. In: Proceedings of the ICASSP, pp. 3875\u20133879. IEEE (2021)","key":"11_CR18","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"11_CR19","first-page":"1659","volume":"14","author":"A Solanki","year":"2019","unstructured":"Solanki, A., Pandey, S.: Music instrument recognition using deep convolutional neural networks. Int. J. Inf. Technol. 14, 1659\u20131668 (2019)","journal-title":"Int. J. Inf. Technol."},{"unstructured":"Wang, H., Zou, Y., Chong, D.: Acoustic scene classification with spectrogram processing strategies. In: Proceedings of 5th the Workshop on Detection and Classification of Acoustic Scenes and Events 2020 (DCASE 2020), Tokyo, Japan (Full Virtual), 2\u20134 November 2020, pp. 210\u2013214 (2020)","key":"11_CR20"},{"doi-asserted-by":"crossref","unstructured":"Xu, Y., Kong, Q., Wang, W., Plumbley, M.D.: Large-scale weakly supervised audio classification using gated convolutional neural network. In: Proceedings of the ICASSP, pp. 121\u2013125. IEEE (2018)","key":"11_CR21","DOI":"10.1109\/ICASSP.2018.8461975"},{"doi-asserted-by":"crossref","unstructured":"Zeyer, A., Bahar, P., Irie, K., Schl\u00fcter, R., Ney, H.: A comparison of transformer and LSTM encoder decoder models for ASR. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 8\u201315. IEEE (2019)","key":"11_CR22","DOI":"10.1109\/ASRU46091.2019.9004025"},{"doi-asserted-by":"crossref","unstructured":"Zhou, W., Michel, W., Irie, K., Kitza, M., Schl\u00fcter, R., Ney, H.: The RWTH ASR system for TED-LIUM release 2: improving hybrid hmm with SpecAugment. In: Proceedings of the ICASSP, pp. 7839\u20137843. IEEE (2020)","key":"11_CR23","DOI":"10.1109\/ICASSP40776.2020.9053573"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44198-1_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T15:31:36Z","timestamp":1730129496000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44198-1_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031441974","9783031441981"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44198-1_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heraklion","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"426","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"22","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"45% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"type of other papers accepted : 9 Abstract","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}