{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T19:02:27Z","timestamp":1747076547293},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030298906"},{"type":"electronic","value":"9783030298913"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-29891-3_29","type":"book-chapter","created":{"date-parts":[[2019,8,22]],"date-time":"2019-08-22T23:12:33Z","timestamp":1566515553000},"page":"330-341","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Sound Transformation: Applying Image Neural Style Transfer Networks to Audio Spectograms"],"prefix":"10.1007","author":[{"given":"Xuehao","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarah Jane","family":"Delany","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Susan","family":"McKeever","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,8,22]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Caetano, M.F., Rodet, X.: Sound morphing by feature interpolation. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 11\u2013231 (2011)","DOI":"10.1109\/ICASSP.2011.5946365"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Dieleman, S., Schrauwen, B.: End-to-end learning for music audio. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6964\u20136968. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6854950"},{"key":"29_CR3","unstructured":"Donahue, J., Kr\u00e4henb\u00fchl, P., Darrell, T.: Adversarial feature learning. arXiv preprint arXiv:1605.09782 (2016)"},{"key":"29_CR4","unstructured":"Engel, J., et al.: Neural audio synthesis of musical notes with wavenet autoencoders. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 1068\u20131077 (2017). JMLR.org"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Frigo, O., Sabater, N., Delon, J., Hellier, P.: Split and match: Example-based adaptive patch sampling for unsupervised style transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 553\u2013561 (2016)","DOI":"10.1109\/CVPR.2016.66"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2414\u20132423 (2016)","DOI":"10.1109\/CVPR.2016.265"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lee, H., Kudlur, M., Dumoulin, V., Shlens, J.: Exploring the structure of a real-time, arbitrary neural artistic stylization network. arXiv preprint arXiv:1705.06830 (2017)","DOI":"10.5244\/C.31.114"},{"issue":"1","key":"29_CR8","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1109\/TASLP.2016.2632307","volume":"25","author":"Y Han","year":"2017","unstructured":"Han, Y., Kim, J., Lee, K., Han, Y., Kim, J., Lee, K.: Deep convolutional neural networks for predominant instrument recognition in polyphonic music. IEEE\/ACM Trans. Audio Speech Lang. Process. (TASLP) 25(1), 208\u2013221 (2017)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process. (TASLP)"},{"key":"29_CR9","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1016\/B978-012505626-7\/50014-5","volume":"2","author":"S Handel","year":"1995","unstructured":"Handel, S.: Timbre perception and auditory object identification. Hearing 2, 425\u2013461 (1995)","journal-title":"Hearing"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Haque, A., Guo, M., Verma, P.: Conditional end-to-end audio transforms. arXiv preprint arXiv:1804.00047 (2018)","DOI":"10.21437\/Interspeech.2018-38"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Hershey, S., et al.: Cnn architectures for large-scale audio classification. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 131\u2013135. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. arXiv preprint (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"29_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Kaneko, T., Kameoka, H., Hiramatsu, K., Kashino, K.: Sequence-to-sequence voice conversion with similarity metric learned using generative adversarial networks. In: Proceedings Interspeech, pp. 1283\u20131287 (2017)","DOI":"10.21437\/Interspeech.2017-970"},{"key":"29_CR15","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"issue":"Nov","key":"29_CR16","first-page":"2579","volume":"9","author":"LVD Maaten","year":"2008","unstructured":"Maaten, L.V.D., Hinton, G.: Visualizing data using t-sne. J. Mach. Learn. Res. 9(Nov), 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Marchi, E., Vesperini, F., Eyben, F., Squartini, S., Schuller, B.: A novel approach for automatic acoustic novelty detection using a denoising autoencoder with bidirectional LSTM neural networks. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1996\u20132000. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178320"},{"key":"29_CR18","unstructured":"Schl\u00fcter, J., Grill, T.: Exploring data augmentation for improved singing voice detection with neural networks. In: ISMIR, pp. 121\u2013126 (2015)"},{"key":"29_CR19","unstructured":"Serra, X., et al.: Musical sound modeling with sinusoids plus noise. Musical Signal Processing, pp. 91\u2013122 (1997)"},{"key":"29_CR20","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"29_CR21","unstructured":"Slaney, M., Covell, M., Lassiter, B.: Automatic audio morphing. In: 1996 IEEE Inter Conference on Acoustics, Speech, and Signal Processing. ICASSP-96. Conference, Proceedings. vol. 2, pp. 1001\u20131004. IEEE (1996)"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: AAAI, vol. 4, p. 12 (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"29_CR23","unstructured":"Verma, P., Smith, J.O.: Neural style transfer for audio spectograms. arXiv preprint arXiv:1801.01589 (2018)"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. arXiv preprint (2017)","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["Lecture Notes in Computer Science","Computer Analysis of Images and Patterns"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-29891-3_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T04:51:16Z","timestamp":1664167876000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-29891-3_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030298906","9783030298913"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-29891-3_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"22 August 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CAIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Analysis of Images and Patterns","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Salerno","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":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"caip2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/caip2019.unisa.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":"176","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":"106","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":"60% - 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":"2.68","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":"3.40","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)"}}]}}