{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T16:38:51Z","timestamp":1743093531963,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031353819"},{"type":"electronic","value":"9783031353826"}],"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\/978-3-031-35382-6_16","type":"book-chapter","created":{"date-parts":[[2023,6,21]],"date-time":"2023-06-21T12:02:39Z","timestamp":1687348959000},"page":"202-213","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Knowledge Transfer from\u00a0Neural Networks for\u00a0Speech Music Classification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7828-503X","authenticated-orcid":false,"given":"Christian","family":"Kehling","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1056-5844","authenticated-orcid":false,"given":"Estefan\u00eda","family":"Cano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,22]]},"reference":[{"key":"16_CR1","doi-asserted-by":"publisher","unstructured":"Arandjelovic, R., Zisserman, A.: Look, listen and learn. In: IEEE International Conference on Computer Vision, pp. 609\u2013617 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.73","DOI":"10.1109\/ICCV.2017.73"},{"issue":"1","key":"16_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13636-019-0152-1","volume":"2019","author":"D de Benito-Gorron","year":"2019","unstructured":"de Benito-Gorron, D., Lozano-Diez, A., Toledano, D.T., Gonzalez-Rodriguez, J.: Exploring convolutional, recurrent, and hybrid deep neural networks for speech and music detection in a large audio dataset. EURASIP J. Audio Speech Music Process. 2019(1), 1\u201318 (2019). https:\/\/doi.org\/10.1186\/s13636-019-0152-1","journal-title":"EURASIP J. Audio Speech Music Process."},{"key":"16_CR3","unstructured":"Choi, K., Fazekas, G., Sandler, M.B., Cho, K.: Transfer learning for music classification and regression tasks. In: Cunningham, S.J., Duan, Z., Hu, X., Turnbull, D. (eds.) Proceedings of the 18th International Society for Music Information Retrieval Conference, ISMIR 2017, Suzhou, China, 23\u201327 October 2017, pp. 141\u2013149 (2017). https:\/\/ismir2017.smcnus.org\/wp-content\/uploads\/2017\/10\/12_Paper.pdf"},{"key":"16_CR4","doi-asserted-by":"publisher","unstructured":"Cramer, J., Wu, H.H., Salamon, J., Bello, J.: Look, listen, and learn more: design choices for deep audio embeddings. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3852\u20133856 (05 2019). https:\/\/doi.org\/10.1109\/ICASSP.2019.8682475","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"16_CR5","unstructured":"Doukhan, D., Lechapt, E., Evrard, M., Carrive, J.: Ina\u2019s mirex 2018 music and speech detection system. In: Music Information Retrieval Evaluation eXchange (MIREX 2018) (2018)"},{"key":"16_CR6","doi-asserted-by":"publisher","unstructured":"Grollmisch, S., Cano, E., Kehling, C., Taenzer, M.: Analyzing the potential of pre-trained embeddings for audio classification tasks. In: 2020 28th European Signal Processing Conference (EUSIPCO), pp. 790\u2013794 (2021). https:\/\/doi.org\/10.23919\/Eusipco47968.2020.9287743","DOI":"10.23919\/Eusipco47968.2020.9287743"},{"key":"16_CR7","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications (2017)"},{"key":"16_CR8","unstructured":"Hussain, M.S., Haque, M.A.: SwishNet: a fast convolutional neural network for speech, music and noise classification and segmentation (2018)"},{"key":"16_CR9","unstructured":"music ir.org: 2015:music\/speech classification and detection results - mirex wiki. https:\/\/www.music-ir.org\/mirex\/wiki\/2015:Music\/Speech_Classification_and_Detection_Results"},{"key":"16_CR10","unstructured":"music ir.org: 2018:music and or speech detection results - mirex wiki. https:\/\/www.music-ir.org\/mirex\/wiki\/2018:Music_and_or_Speech_Detection_Results"},{"key":"16_CR11","doi-asserted-by":"publisher","first-page":"1067","DOI":"10.1007\/s00521-019-04076-1","volume":"32","author":"J Kim","year":"2020","unstructured":"Kim, J., Urbano, J., Liem, C.C.S., Hanjalic, A.: One deep music representation to rule them all?: a comparative analysis of different representation learning strategies. Neural Comput. Appl. 32, 1067\u20131093 (2020)","journal-title":"Neural Comput. Appl."},{"key":"16_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2017)"},{"key":"16_CR13","doi-asserted-by":"publisher","first-page":"2880","DOI":"10.1109\/TASLP.2020.3030497","volume":"28","author":"Q Kong","year":"2020","unstructured":"Kong, Q., Cao, Y., Iqbal, T., Wang, Y., Wang, W., Plumbley, M.D.: PANNs: large-scale pretrained audio neural networks for audio pattern recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 28, 2880\u20132894 (2020). https:\/\/doi.org\/10.1109\/TASLP.2020.3030497","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"16_CR14","unstructured":"Kruspe, A., Zapf, D., Lukashevich, H.: Automatic speech\/music discrimination for broadcast signals. In: Proceedings - Series of the Gesellschaft fuer Informatik (GI). Lecture Notes in Informatics (LNI) (2017)"},{"key":"16_CR15","unstructured":"Lidy, T.: Spectral convolutional neural network for music classification. Music information retrieval evaluation eX-change (MIREX) (2015)"},{"key":"16_CR16","unstructured":"Marolt, M.: Probabilistic segmentation and labeling of ethnomusicological field recordings. In: Proceedings of ISMIR (2009)"},{"key":"16_CR17","doi-asserted-by":"publisher","first-page":"439","DOI":"10.3390\/app9030439","volume":"9","author":"M Marolt","year":"2019","unstructured":"Marolt, M., Bohak, C., Kavcic, A., Pesek, M.: Automatic segmentation of ethnomusicological field recordings. Appl. Sci. 9, 439 (2019). https:\/\/doi.org\/10.3390\/app9030439","journal-title":"Appl. Sci."},{"key":"16_CR18","unstructured":"millionsongdataset.com: Welcome! | million song dataset. https:\/\/millionsongdataset.com\/"},{"key":"16_CR19","doi-asserted-by":"publisher","unstructured":"Mora-\u00c1ngel, F., Gil, G.A.L., Cano, E., Grollmisch, S.: ACMUS-MIR: an annotated dataset of Andean Colombian music. In: In 7th International Conference on Digital Libraries for Musicology. Delft, The Netherlands (2019). https:\/\/doi.org\/10.5281\/zenodo.3268961","DOI":"10.5281\/zenodo.3268961"},{"key":"16_CR20","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1016\/j.eswa.2018.05.016","volume":"114","author":"M Papakostas","year":"2018","unstructured":"Papakostas, M., Giannakopoulos, T.: Speech-music discrimination using deep visual feature extractors. Expert Syst. Appl. 114, 334\u2013344 (2018)","journal-title":"Expert Syst. Appl."},{"key":"16_CR21","unstructured":"research.google.com: Audioset. https:\/\/research.google.com\/audioset\/"},{"key":"16_CR22","unstructured":"Sakashita, Y., Aono, M.: Acoustic scene classification by ensemble of spectrograms based on adaptive temporal divisions. Technical report, DCASE2018 Challenge (2018)"},{"key":"16_CR23","unstructured":"Scheirer, E., Slaney, M.: Construction and evaluation of a robust multifeature speech\/music discriminator. IEEE International Conference on Acoustics, Speech, Signal Processing (ICASSP 1997) (1997)"},{"key":"16_CR24","unstructured":"Snyder, D., Chen, G., Povey, D.: MUSAN: a music, speech, and noise corpus (2015)"},{"key":"16_CR25","unstructured":"Tzanetakis, G.: marsyas.info GTZAN speech music dataset download. https:\/\/opihi.cs.uvic.ca\/sound\/music_speech.tar.gz"}],"container-title":["Lecture Notes in Computer Science","Music in the AI Era"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-35382-6_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,21]],"date-time":"2023-06-21T12:05:08Z","timestamp":1687349108000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-35382-6_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031353819","9783031353826"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-35382-6_16","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 June 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CMMR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Computer Music Multidisciplinary Research","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cmmr2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cmmr2021.gttm.jp\/committee\/","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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"48","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":"24","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":"0","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":"50% - 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":"3","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)"}}]}}