{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T18:16:45Z","timestamp":1742926605720,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031299551"},{"type":"electronic","value":"9783031299568"}],"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\/978-3-031-29956-8_22","type":"book-chapter","created":{"date-parts":[[2023,4,4]],"date-time":"2023-04-04T23:03:58Z","timestamp":1680649438000},"page":"341-356","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Transposition of\u00a0Simple Waveforms from\u00a0Raw Audio with\u00a0Deep Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1033-5931","authenticated-orcid":false,"given":"Patrick J.","family":"Donnelly","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1856-5088","authenticated-orcid":false,"given":"Parker","family":"Carlson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,1]]},"reference":[{"issue":"5","key":"22_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.7551\/mitpress\/7496.003.0016","volume":"34","author":"Y Bengio","year":"2007","unstructured":"Bengio, Y., LeCun, Y., et al.: Scaling learning algorithms towards AI. Large-Scale Kernel Mach. 34(5), 1\u201341 (2007). https:\/\/doi.org\/10.7551\/mitpress\/7496.003.0016","journal-title":"Large-Scale Kernel Mach."},{"issue":"4","key":"22_CR2","doi-asserted-by":"publisher","first-page":"981","DOI":"10.1007\/s00521-018-3813-6","volume":"32","author":"J-P Briot","year":"2018","unstructured":"Briot, J.-P., Pachet, F.: Deep learning for music generation: challenges and directions. Neural Comput. Appl. 32(4), 981\u2013993 (2018). https:\/\/doi.org\/10.1007\/s00521-018-3813-6","journal-title":"Neural Comput. Appl."},{"key":"22_CR3","doi-asserted-by":"publisher","unstructured":"Choi, K., Fazekas, G., Cho, K., Sandler, M.: A tutorial on deep learning for music information retrieval. arXiv preprint arXiv:1709.04396 (2017). https:\/\/doi.org\/10.48550\/arXiv.1709.04396","DOI":"10.48550\/arXiv.1709.04396"},{"key":"22_CR4","doi-asserted-by":"publisher","unstructured":"Disch, S., Edler, B.: Frequency selective pitch transposition of audio signals. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 29\u201332. IEEE (2011). https:\/\/doi.org\/10.1109\/ICASSP.2011.5946320","DOI":"10.1109\/ICASSP.2011.5946320"},{"issue":"4","key":"22_CR5","doi-asserted-by":"publisher","first-page":"14","DOI":"10.2307\/3680093","volume":"10","author":"M Dolson","year":"1986","unstructured":"Dolson, M.: The phase vocoder: a tutorial. Comput. Music. J. 10(4), 14\u201327 (1986). https:\/\/doi.org\/10.2307\/3680093","journal-title":"Comput. Music. J."},{"key":"22_CR6","unstructured":"Engel, J., Hantrakul, L.H., Gu, C., Roberts, A.: DDSP: differentiable digital signal processing. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=B1x1ma4tDr"},{"key":"22_CR7","doi-asserted-by":"publisher","unstructured":"Engel, J., et al.: Neural audio synthesis of musical notes with wavenet autoencoders. In: International Conference on Machine Learning, pp. 1068\u20131077. PMLR (2017). https:\/\/doi.org\/10.48550\/arXiv.1704.01279","DOI":"10.48550\/arXiv.1704.01279"},{"key":"22_CR8","doi-asserted-by":"publisher","unstructured":"Hernandez-Olivan, C., Beltran, J.R.: Music composition with deep learning: a review. arXiv preprint arXiv:2108.12290 (2021). https:\/\/doi.org\/10.48550\/arXiv:2108.12290","DOI":"10.48550\/arXiv:2108.12290"},{"key":"22_CR9","doi-asserted-by":"publisher","unstructured":"Jawahir, A., Haviluddin, H.: An audio encryption using transposition method. Int. J. Adv. Intell. Inform. 1(2), 98\u2013106 (2015). https:\/\/doi.org\/10.26555\/ijain.v1i2.24","DOI":"10.26555\/ijain.v1i2.24"},{"key":"22_CR10","doi-asserted-by":"publisher","first-page":"117327","DOI":"10.3390\/app9194050","volume":"7","author":"RA Khalil","year":"2019","unstructured":"Khalil, R.A., Jones, E., Babar, M.I., Jan, T., Zafar, M.H., Alhussain, T.: Speech emotion recognition using deep learning techniques: a review. IEEE Access 7, 117327\u2013117345 (2019). https:\/\/doi.org\/10.3390\/app9194050","journal-title":"IEEE Access"},{"issue":"3","key":"22_CR11","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1017\/S135577180000306X","volume":"4","author":"B Lawlor","year":"2000","unstructured":"Lawlor, B., Fagan, A.D.: A novel efficient algorithm for music transposition. Organ. Sound 4(3), 161\u2013167 (2000). https:\/\/doi.org\/10.1017\/S135577180000306X","journal-title":"Organ. Sound"},{"key":"22_CR12","doi-asserted-by":"publisher","unstructured":"Lin, S., Liu, N., Nazemi, M., Li, H., Ding, C., Wang, Y., Pedram, M.: FFT-based deep learning deployment in embedded systems. In: 2018 Design, Automation and Test in Europe Conference and Exhibition (DATE), pp. 1045\u20131050. IEEE (2018). https:\/\/doi.org\/10.23919\/DATE.2018.8342166","DOI":"10.23919\/DATE.2018.8342166"},{"key":"22_CR13","doi-asserted-by":"publisher","unstructured":"Luo, Y.J., Chen, M.T., Chi, T.S., Su, L.: Singing voice correction using canonical time warping. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 156\u2013160. IEEE (2018). https:\/\/doi.org\/10.1109\/ICASSP.2018.8461280","DOI":"10.1109\/ICASSP.2018.8461280"},{"key":"22_CR14","doi-asserted-by":"publisher","unstructured":"Luo, Y.J., Lin, Y.J., Su, L.: Toward expressive singing voice correction: On perceptual validity of evaluation metrics for vocal melody extraction. arXiv preprint arXiv:2010.12196 (2020). https:\/\/doi.org\/10.48550\/arXiv.2010.12196","DOI":"10.48550\/arXiv.2010.12196"},{"key":"22_CR15","doi-asserted-by":"publisher","unstructured":"Mathieu, M., Henaff, M., LeCun, Y.: Fast training of convolutional networks through FFTs. arXiv preprint arXiv:1312.5851 (2013). https:\/\/doi.org\/10.48550\/arXiv.1312.5851","DOI":"10.48550\/arXiv.1312.5851"},{"issue":"5\u20136","key":"22_CR16","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1016\/0167-6393(90)90021-Z","volume":"9","author":"E Moulines","year":"1990","unstructured":"Moulines, E., Charpentier, F.: Pitch-synchronous waveform processing techniques for text-to-speech synthesis using diphones. Speech Commun. 9(5\u20136), 453\u2013467 (1990). https:\/\/doi.org\/10.1016\/0167-6393(90)90021-Z","journal-title":"Speech Commun."},{"key":"22_CR17","doi-asserted-by":"publisher","unstructured":"Nye, M., Saxe, A.: Are efficient deep representations learnable? arXiv preprint arXiv:1807.06399 (2018). https:\/\/doi.org\/10.48550\/arXiv.1807.06399","DOI":"10.48550\/arXiv.1807.06399"},{"key":"22_CR18","doi-asserted-by":"publisher","unstructured":"van den Oord, A., et al.: Wavenet: a generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016). https:\/\/doi.org\/10.48550\/arXiv.1609.03499","DOI":"10.48550\/arXiv.1609.03499"},{"key":"22_CR19","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1007\/978-3-030-74478-6_10","volume-title":"Multi-faceted Deep Learning","author":"G Peeters","year":"2021","unstructured":"Peeters, G., Richard, G.: Deep learning for audio and music. In: Benois-Pineau, J., Zemmari, A. (eds.) Multi-faceted Deep Learning, pp. 231\u2013266. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-74478-6_10"},{"issue":"2","key":"22_CR20","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1109\/JSTSP.2019.2908700","volume":"13","author":"H Purwins","year":"2019","unstructured":"Purwins, H., Li, B., Virtanen, T., Schl\u00fcter, J., Chang, S.Y., Sainath, T.: Deep learning for audio signal processing. IEEE J. Sel. Top. Sig. Process. 13(2), 206\u2013219 (2019). https:\/\/doi.org\/10.1109\/JSTSP.2019.2908700","journal-title":"IEEE J. Sel. Top. Sig. Process."},{"key":"22_CR21","doi-asserted-by":"publisher","unstructured":"Rosenzweig, S., Schw\u00e4r, S., Driedger, J., M\u00fcller, M.: Adaptive pitch-shifting with applications to intonation adjustment in a cappella recordings. In: 2021 24th International Conference on Digital Audio Effects (DAFx), pp. 121\u2013128. IEEE (2021). https:\/\/doi.org\/10.23919\/DAFx51585.2021.9768268","DOI":"10.23919\/DAFx51585.2021.9768268"},{"key":"22_CR22","doi-asserted-by":"publisher","unstructured":"Roucos, S., Wilgus, A.: High quality time-scale modification for speech. In: ICASSP\u201985. IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 10, pp. 493\u2013496. IEEE (1985). https:\/\/doi.org\/10.1109\/ICASSP.1985.1168381","DOI":"10.1109\/ICASSP.1985.1168381"},{"key":"22_CR23","doi-asserted-by":"publisher","unstructured":"Schedl, M.: Deep learning in music recommendation systems. Front. Appl. Math. Stat. 44 (2019). https:\/\/doi.org\/10.3389\/fams.2019.00044","DOI":"10.3389\/fams.2019.00044"},{"key":"22_CR24","doi-asserted-by":"publisher","unstructured":"Verhelst, W., Roelands, M.: An overlap-add technique based on waveform similarity (WSOLA) for high quality time-scale modification of speech. In: 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 2, pp. 554\u2013557. IEEE (1993). https:\/\/doi.org\/10.1109\/ICASSP.1993.319366","DOI":"10.1109\/ICASSP.1993.319366"},{"key":"22_CR25","doi-asserted-by":"publisher","unstructured":"Wager, S., Tzanetakis, G., Wang, C.i., Kim, M.: Deep autotuner: a pitch correcting network for singing performances. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 246\u2013250. IEEE (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9054308","DOI":"10.1109\/ICASSP40776.2020.9054308"},{"key":"22_CR26","doi-asserted-by":"publisher","unstructured":"Zhou, F., Torre, F.d.l.: Canonical time warping for alignment of human behavior. In: Proceedings of the 22nd International Conference on Neural Information Processing Systems. NIPS 2009, pp. 2286\u20132294. Curran Associates Inc., Red Hook (2009). https:\/\/doi.org\/10.5555\/2984093.2984349","DOI":"10.5555\/2984093.2984349"},{"key":"22_CR27","doi-asserted-by":"publisher","unstructured":"Zou, F., Shen, L., Jie, Z., Zhang, W., Liu, W.: A sufficient condition for convergences of Adam and RMSPROP. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11127\u201311135 (2019). https:\/\/doi.org\/10.48550\/arXiv.1811.09358","DOI":"10.48550\/arXiv.1811.09358"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in Music, Sound, Art and Design"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-29956-8_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T19:44:58Z","timestamp":1710359098000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-29956-8_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031299551","9783031299568"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-29956-8_22","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":"1 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EvoMUSART","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Intelligence in Music, Sound, Art and Design (Part of EvoStar)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brno","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","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":"12 April 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 April 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"evomusart2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.evostar.org\/2023\/evomusart\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"55","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":"20","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":"7","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":"36% - 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":"3","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)"}}]}}