{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:32:21Z","timestamp":1753601541064,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031037887"},{"type":"electronic","value":"9783031037894"}],"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\/978-3-031-03789-4_20","type":"book-chapter","created":{"date-parts":[[2022,4,14]],"date-time":"2022-04-14T23:02:49Z","timestamp":1649977369000},"page":"308-322","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Sound Model Factory: An Integrated System Architecture for\u00a0Generative Audio Modelling"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9200-1048","authenticated-orcid":false,"given":"Lonce","family":"Wyse","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0351-6574","authenticated-orcid":false,"given":"Purnima","family":"Kamath","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1350-9095","authenticated-orcid":false,"given":"Chitralekha","family":"Gupta","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,4,15]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Antognini, J.M., Hoffman, M., Weiss, R.J.: Audio texture synthesis with random neural networks: improving diversity and quality. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3587\u20133591. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682598"},{"key":"20_CR2","unstructured":"Arjovsky, M., Bottou, L.: Towards principled methods for training generative adversarial networks. arXiv preprint arXiv:1701.04862 (2017)"},{"key":"20_CR3","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: International Conference on Machine Learning, pp. 214\u2013223. PMLR (2017)"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Caracalla, H., Roebel, A.: Sound texture synthesis using RI spectrograms. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 416\u2013420. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053376"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"20_CR6","unstructured":"Engel, J., Agrawal, K.K., Chen, S., Gulrajani, I., Donahue, C., Roberts, A.: Gansynth: adversarial neural audio synthesis. arXiv preprint arXiv:1902.08710 (2019)"},{"key":"20_CR7","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)"},{"key":"20_CR8","unstructured":"Esling, P., Bitton, A., et al.: Generative timbre spaces: regularizing variational auto-encoders with perceptual metrics. arXiv preprint arXiv:1805.08501 (2018)"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Gatys, L., Ecker, A.S., Bethge, M.: Texture synthesis using convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 262\u2013270 (2015)","DOI":"10.1109\/CVPR.2016.265"},{"key":"20_CR10","unstructured":"Goodfellow, I.: Nips 2016 tutorial: generative adversarial networks. arXiv preprint arXiv:1701.00160 (2016)"},{"issue":"2","key":"20_CR11","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 shorttime Fourier transform. IEEE Trans. Audio Speech Lang. Process. 32(2), 236\u2013243 (1984)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Grinstein, E., Duong, N.Q., Ozerov, A., P\u00e9rez, P.: Audio style transfer. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 586\u2013590. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461711"},{"key":"20_CR13","unstructured":"Gupta, C., Kamath, P., Wyse, L.: Signal representations for synthesizing audio textures with generative adversarial networks. arXiv preprint arXiv:2103.07390 (2021)"},{"issue":"4","key":"20_CR14","doi-asserted-by":"publisher","first-page":"1051","DOI":"10.1007\/s00521-019-04053-8","volume":"32","author":"M Huzaifah bin Md Shahrin","year":"2019","unstructured":"Huzaifah bin Md Shahrin, M., Wyse, L.: Applying visual domain style transfer and texture synthesis techniques to audio: insights and challenges. Neural Comput. Appl. 32(4), 1051\u20131065 (2019). https:\/\/doi.org\/10.1007\/s00521-019-04053-8","journal-title":"Neural Comput. Appl."},{"key":"20_CR15","unstructured":"Jahanian, A., Chai, L., Isola, P.: On the \u201csteerability\u201d of generative adversarial networks. arXiv preprint arXiv:1907.07171 (2019)"},{"key":"20_CR16","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of gans for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017)"},{"key":"20_CR17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-88163-3","volume-title":"Self-Organization and Associative Memory","author":"T Kohonen","year":"1989","unstructured":"Kohonen, T.: Self-Organization and Associative Memory, 3rd edn. Springer, Heidelberg (1989). https:\/\/doi.org\/10.1007\/978-3-642-88163-3","edition":"3"},{"key":"20_CR18","unstructured":"Mao, W., Lou, B., Yuan, J.: Tunagan: interpretable gan for smart editing. arXiv preprint arXiv:1908.06163 (2019)"},{"key":"20_CR19","unstructured":"Marafioti, A., Perraudin, N., Holighaus, N., Majdak, P.: Adversarial generation of time-frequency features with application in audio synthesis. In: International Conference on Machine Learning, pp. 4352\u20134362. PMLR (2019)"},{"key":"20_CR20","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Nistal, J., Lattner, S., Richard, G.: Comparing representations for audio synthesis using generative adversarial networks. In: 2020 28th European Signal Processing Conference (EUSIPCO), pp. 161\u2013165. IEEE (2021)","DOI":"10.23919\/Eusipco47968.2020.9287799"},{"key":"20_CR22","unstructured":"Nistal, J., Lattner, S., Richard, G.: Drumgan: synthesis of drum sounds with timbral feature conditioning using generative adversarial networks. arXiv preprint arXiv:2008.12073 (2020)"},{"key":"20_CR23","unstructured":"van den Oord, A., et al.: Wavenet: a generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016)"},{"key":"20_CR24","unstructured":"Palanisamy, K., Singhania, D., Yao, A.: Rethinking CNN models for audio classification. arXiv preprint arXiv:2007.11154 (2020)"},{"issue":"5","key":"20_CR25","doi-asserted-by":"publisher","first-page":"1154","DOI":"10.1109\/TASLP.2017.2678166","volume":"25","author":"Z Pr\u016f\u0161a","year":"2017","unstructured":"Pr\u016f\u0161a, Z., Balazs, P., S\u00f8ndergaard, P.L.: A noniterative method for reconstruction of phase from STFT magnitude. IEEE\/ACM Trans. Audio Speech Lang. Process. 25(5), 1154\u20131164 (2017)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"20_CR26","first-page":"2234","volume":"29","author":"T Salimans","year":"2016","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training gans. Adv. Neural Inf. Process. Syst. 29, 2234\u20132242 (2016)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"20_CR27","unstructured":"Ulyanov, D., Lebedev, V.: Audio texture synthesis and style transfer. https:\/\/dmitryulyanov.github.io\/audio-texture-synthesis-and-style-transfer\/ (2016). Accessed 10 July 2019"},{"key":"20_CR28","unstructured":"Wyse, L.: Real-valued parametric conditioning of an rnn for interactive sound synthesis. In: Proceedings of the 6th International Workshop on Musical Metacreation, ACM Conference on Computational Creativity, Salamanca (2018)"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Xia, W., Zhang, Y., Yang, Y., Xue, J.H., Zhou, B., Yang, M.H.: Gan inversion: a survey. arXiv preprint arXiv:2101.05278 (2021)","DOI":"10.1109\/TPAMI.2022.3181070"}],"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\/978-3-031-03789-4_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T02:49:09Z","timestamp":1675306149000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-03789-4_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031037887","9783031037894"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-03789-4_20","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":"15 April 2022","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":"Madrid","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","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":"20 April 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 April 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"evomusart2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.evostar.org\/2022\/","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":"51","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":"6","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":"39% - 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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}