{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T21:54:00Z","timestamp":1743112440884,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031165634"},{"type":"electronic","value":"9783031165641"}],"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\/978-3-031-16564-1_36","type":"book-chapter","created":{"date-parts":[[2022,9,25]],"date-time":"2022-09-25T23:02:43Z","timestamp":1664146963000},"page":"378-387","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Audio Super-Resolution via\u00a0Vision Transformer"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7386-2512","authenticated-orcid":false,"given":"Simona","family":"Nistic\u00f2","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4915-5137","authenticated-orcid":false,"given":"Luigi","family":"Palopoli","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4891-4533","authenticated-orcid":false,"given":"Adele Pia","family":"Romano","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,9,26]]},"reference":[{"key":"36_CR1","unstructured":"https:\/\/huggingface.co\/docs\/transformers\/index"},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Andreev, P., Alanov, A., Ivanov, O., Vetrov, D.: HiFi++: a unified framework for neural vocoding, bandwidth extension and speech enhancement. arXiv preprint arXiv:2203.13086 (2022)","DOI":"10.1109\/ICASSP49357.2023.10097255"},{"key":"36_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., Yang, J.: Speech bandwidth extension based on Wasserstein generative adversarial network. In: 2021 IEEE 21st International Conference on Communication Technology (ICCT), pp. 1356\u20131362. IEEE (2021)","DOI":"10.1109\/ICCT52962.2021.9658055"},{"key":"36_CR4","doi-asserted-by":"crossref","unstructured":"Dai, J., Zhang, Y., Xie, P., Xu, X.: Super-resolution for music signals using generative adversarial networks. In: 2021 IEEE 4th International Conference on Big Data and Artificial Intelligence (BDAI), pp. 1\u20135. IEEE (2021)","DOI":"10.1109\/BDAI52447.2021.9515219"},{"key":"36_CR5","unstructured":"Defferrard, M., Benzi, K., Vandergheynst, P., Bresson, X.: FMA: a dataset for music analysis. arXiv preprint arXiv:1612.01840 (2016)"},{"key":"36_CR6","doi-asserted-by":"crossref","unstructured":"Erell, A., Weintraub, M.: Estimation using log-spectral-distance criterion for noise-robust speech recognition. In: International Conference on Acoustics, Speech, and Signal Processing, pp. 853\u2013856. IEEE (1990)","DOI":"10.1109\/ICASSP.1991.150487"},{"issue":"2","key":"36_CR7","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1109\/TASSP.1984.1164317","volume":"32","author":"D Griffin","year":"1984","unstructured":"Griffin, D., Lim, J.: Signal estimation from modified short-time Fourier transform. IEEE Trans. Acoust. Speech Signal Process. 32(2), 236\u2013243 (1984)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"36_CR8","unstructured":"Guo, M.H., et al.: Attention mechanisms in computer vision: a survey. arXiv preprint arXiv:2111.07624 (2021)"},{"key":"36_CR9","unstructured":"Huang, C.Z.A., et al.: Music transformer. arXiv preprint arXiv:1809.04281 (2018)"},{"issue":"12","key":"36_CR10","doi-asserted-by":"publisher","first-page":"2088","DOI":"10.4249\/scholarpedia.2088","volume":"1","author":"DH Johnson","year":"2006","unstructured":"Johnson, D.H.: Signal-to-noise ratio. Scholarpedia 1(12), 2088 (2006)","journal-title":"Scholarpedia"},{"key":"36_CR11","doi-asserted-by":"crossref","unstructured":"Kim, J., Englebienne, G., Truong, K.P., Evers, V.: Deep temporal models using identity skip-connections for speech emotion recognition. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 1006\u20131013 (2017)","DOI":"10.1145\/3123266.3123353"},{"key":"36_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"36_CR13","unstructured":"Kolesnikov, A., et al.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale (2021)"},{"key":"36_CR14","unstructured":"Kuleshov, V., Enam, S.Z., Ermon, S.: Audio super resolution using neural networks. arXiv preprint arXiv:1708.00853 (2017)"},{"key":"36_CR15","unstructured":"Kuleshov, V., Enam, S.Z., Ermon, S.: Audio super resolution using neural networks. arXiv preprint arXiv:1708.00853 (2017)"},{"key":"36_CR16","doi-asserted-by":"crossref","unstructured":"Li, K., Lee, C.H.: A deep neural network approach to speech bandwidth expansion. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4395\u20134399. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178801"},{"key":"36_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Y.: Recovery of lossy compressed music based on CNN super-resolution and GAN. In: 2021 IEEE 3rd International Conference on Frontiers Technology of Information and Computer (ICFTIC), pp. 623\u2013629. IEEE (2021)","DOI":"10.1109\/ICFTIC54370.2021.9647041"},{"key":"36_CR18","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"McFee, B., et al.: librosa: audio and music signal analysis in python. In: Proceedings of the 14th Python in Science Conference, vol. 8, pp. 18\u201325. Citeseer (2015)","DOI":"10.25080\/Majora-7b98e3ed-003"},{"issue":"1","key":"36_CR20","first-page":"1049","volume":"45","author":"S McKinley","year":"1998","unstructured":"McKinley, S., Levine, M.: Cubic spline interpolation. Coll. Redwoods 45(1), 1049\u20131060 (1998)","journal-title":"Coll. Redwoods"},{"key":"36_CR21","unstructured":"Oyedotun, O.K., Al Ismaeil, K., Aouada, D.: Why is everyone training very deep neural network with skip connections? IEEE Trans. Neural Netw. Learn. Syst., 1\u201315 (2022)"},{"key":"36_CR22","doi-asserted-by":"crossref","unstructured":"Podder, P., Khan, T.Z., Khan, M.H., Rahman, M.M.: Comparative performance analysis of hamming, hanning and blackman window. Int. J. Comput. Appl. 96(18), 1\u20137 (2014)","DOI":"10.5120\/16891-6927"},{"key":"36_CR23","doi-asserted-by":"crossref","unstructured":"Smaragdis, P., Raj, B.: Example-driven bandwidth expansion. In: 2007 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, pp. 135\u2013138. IEEE (2007)","DOI":"10.1109\/ASPAA.2007.4393004"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Su, J., Wang, Y., Finkelstein, A., Jin, Z.: Bandwidth extension is all you need. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 696\u2013700. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9413575"},{"key":"36_CR25","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, D.: Time-frequency loss for CNN based speech super-resolution. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 861\u2013865. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053712"},{"key":"36_CR26","doi-asserted-by":"publisher","first-page":"2058","DOI":"10.1109\/TASLP.2021.3054302","volume":"29","author":"H Wang","year":"2021","unstructured":"Wang, H., Wang, D.: Towards robust speech super-resolution. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 2058\u20132066 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."}],"container-title":["Lecture Notes in Computer Science","Foundations of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-16564-1_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T13:26:55Z","timestamp":1710336415000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16564-1_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031165634","9783031165641"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16564-1_36","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":"26 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISMIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Methodologies for Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cosenza","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"3 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 October 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":"ismis2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ismis2022.icar.cnr.it\/","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":"71","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":"31","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":"11","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":"44% - 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":"3.7","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":"2","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)"}},{"value":"Number and type of other papers accepted :\t4 industrial papers","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)"}}]}}