{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T21:14:31Z","timestamp":1742937271173,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031059803"},{"type":"electronic","value":"9783031059810"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-05981-0_14","type":"book-chapter","created":{"date-parts":[[2022,5,9]],"date-time":"2022-05-09T12:02:50Z","timestamp":1652097770000},"page":"173-186","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["BaDumTss: Multi-task Learning for\u00a0Beatbox Transcription"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4124-4813","authenticated-orcid":false,"given":"Priya","family":"Mehta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4538-3845","authenticated-orcid":false,"given":"Meet","family":"Maheshwari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7607-4119","authenticated-orcid":false,"given":"Brihi","family":"Joshi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0210-0369","authenticated-orcid":false,"given":"Tanmoy","family":"Chakraborty","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,10]]},"reference":[{"key":"14_CR1","unstructured":"Cazau, D., Wang, Y., Adam, O., Wang, Q., Nuel, G.: Improving note segmentation in automatic piano music transcription systems with a two-state pitch-wise HMM method. In: ISMIR (2017)"},{"key":"14_CR2","unstructured":"Ishizuka, R., Nishikimi, R., Nakamura, E., Yoshii, K.: Tatum-level drum transcription based on a convolutional recurrent neural network with language model-based regularized training (2020)"},{"key":"14_CR3","unstructured":"Choi, K., Cho, K.: Deep unsupervised drum transcription (2019)"},{"key":"14_CR4","doi-asserted-by":"publisher","unstructured":"Southall, C., Stables, R., Hockman, S.: Automatic drum transcription for polyphonic recordings using soft attention mechanisms and convolutional neural networks. In: Proceedings of the 18th International Society for Music Information Retrieval Conference (2017). https:\/\/doi.org\/10.5281\/zenodo.1415616","DOI":"10.5281\/zenodo.1415616"},{"key":"14_CR5","unstructured":"Hawthorne, C., et al.: Onsets and frames: dual-objective piano transcription (2018)"},{"key":"14_CR6","unstructured":"Wang, Y., Salamon, J., Cartwright, M., Bryan, N.J., Pablo Bello, J.: Few-shot drum transcription in polyphonic music. In: Proceedings of the 21th International Society for Music Information Retrieval Conference, ISMIR 2020, Montreal, Canada, 11\u201316 October 2020"},{"key":"14_CR7","unstructured":"Callender, L., Hawthorne, C., Engel, J.: Improving perceptual quality of drum transcription with the expanded groove MIDI Dataset (2020)"},{"key":"14_CR8","unstructured":"Hawthorne, C., et al.: Enabling factorized piano music modeling and generation with the MAESTRO dataset. In: International Conference on Learning Representations (2019)"},{"key":"14_CR9","unstructured":"Sinyor, E., McKay, C., Fiebrink, R., McEnnis, D., Fujinaga, F.: Beatbox classification using ACE. In: ISMIR (2005)"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Picart, B., Brognaux, B., Dupont, S.: Analysis and automatic recognition of Human BeatBox sounds: a comparative study. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","DOI":"10.1109\/ICASSP.2015.7178773"},{"key":"14_CR11","unstructured":"Evain, S., et al.: Beatbox sounds recognition using a speech-dedicated HMM-GMM based system. In: Models and Analisys of Vocal Emission for Biomedical Applications Firenze, Italy (2019)"},{"key":"14_CR12","unstructured":"librosa\/librosa: 0.8.0. https:\/\/doi.org\/10.5281\/zenodo.3955228"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Weng, W., et al.: U-Net: convolutional networks for biomedical image segmentation. IEEE Access 9, 16591\u201316603 (2015)","DOI":"10.1109\/ACCESS.2021.3053408"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Pedersoli, F., Tzanetakis, G., Yi, K.M.: Improving music transcription by pre-stacking AU-Net. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","DOI":"10.1109\/ICASSP40776.2020.9052987"},{"key":"14_CR15","unstructured":"Cartwright, M., Bello, J.P.: Increasing drum transcription vocabulary using data synthesis. In: Proceedings of the International Conference on Digital Audio Effects (DAFx) (2018)"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Cheuk, K.W., Agres, K., Herremans, D.: The impact of Audio input representations on neural network based music transcription. In: 2020 International Joint Conference on Neural Networks (IJCNN) (2020)","DOI":"10.1109\/IJCNN48605.2020.9207605"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Kong, Q., Li, B., Song, X., Wan, Y., Wang, Y.: High-resolution Piano transcription with pedals by regressing onsets and offsets times (2020)","DOI":"10.1109\/TASLP.2021.3121991"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Jacques, C., Roebel, A.: Data augmentation for drum transcription with convolutional neural networks. In: 2019 27th European Signal Processing Conference (EUSIPCO) (2019)","DOI":"10.23919\/EUSIPCO.2019.8902980"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Delgado, A., McDonald, S., Xu, N., Sandler, M.: A new dataset for amateur vocal percussion analysis. In: Proceedings of the 14th International Audio Mostly Conference: A Journey in Sound (2019)","DOI":"10.1145\/3356590.3356844"},{"issue":"1","key":"14_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2007\/48317","volume":"2007","author":"GE Poliner","year":"2007","unstructured":"Poliner, G.E., Ellis, D.P.W.: A Discriminative Model for Polyphonic Piano Transcription. EURASIP J. Adv. Signal Process. 2007(1), 1\u20139 (2007). https:\/\/doi.org\/10.1155\/2007\/48317","journal-title":"EURASIP J. Adv. Signal Process."},{"issue":"1","key":"14_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2007\/48317","volume":"2007","author":"GE Poliner","year":"2007","unstructured":"Poliner, G.E., Ellis, D.P.W.: A Discriminative Model for Polyphonic Piano Transcription. EURASIP Journal on Advances in Signal Processing 2007(1), 1\u20139 (2007). https:\/\/doi.org\/10.1155\/2007\/48317","journal-title":"EURASIP Journal on Advances in Signal Processing"},{"key":"14_CR22","doi-asserted-by":"publisher","unstructured":"Vogl, R., Dorfer, M., Knees,P.: Drum transcription from polyphonic music with recurrent neural networks. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2017). https:\/\/doi.org\/10.1109\/ICASSP.2017.7952146","DOI":"10.1109\/ICASSP.2017.7952146"},{"key":"14_CR23","unstructured":"Vogl, R., Widmer, G., Knees, P.: Towards multi-instrument rum transcription. In: Proceedings of the 21st International Conference on Digital Audio Effects (DAFx 2018), 4\u20138 September 2018, Aveiro, Portugal (2018)"},{"key":"14_CR24","doi-asserted-by":"publisher","unstructured":"Gillet, O., Richard, G.: ENST-drums: an extensive audio-visual database for drum signals processing. In: Proceedings of the 7th International Conference on Music Information Retrieval (2006). https:\/\/doi.org\/10.5281\/zenodo.1415902","DOI":"10.5281\/zenodo.1415902"},{"key":"14_CR25","unstructured":"Emiya, V., Bertin, N., David, B., Badeau, R.: MAPS - a piano database for multipitch estimation and automatic transcription of music. Res. Rep. 11., 00544155 (2010)"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-05981-0_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T13:38:48Z","timestamp":1710337128000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-05981-0_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031059803","9783031059810"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-05981-0_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"10 May 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chengdu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 May 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 May 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/pakdd.net\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"558","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":"121","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":"22% - 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":"3.75","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":"6.45","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}