{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T18:03:33Z","timestamp":1779818613952,"version":"3.53.1"},"publisher-location":"Singapore","reference-count":11,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819620739","type":"print"},{"value":"9789819620746","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-2074-6_27","type":"book-chapter","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T11:10:52Z","timestamp":1735643452000},"page":"233-239","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Transformer-Based Audio Generation Conditioned by\u00a02D Latent Maps: A Demonstration"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4903-3933","authenticated-orcid":false,"given":"Christian","family":"Limberg","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9193-5973","authenticated-orcid":false,"given":"Marc A.","family":"Kastner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,1]]},"reference":[{"key":"27_CR1","unstructured":"Agostinelli, A., et al.: MusicLM: generating music from text. arXiv preprint arXiv:2301.11325 (2023)"},{"key":"27_CR2","unstructured":"Aouameur, C., Esling, P., Hadjeres, G.: Neural drum machine : an interactive system for real-time synthesis of drum sounds (2019)"},{"key":"27_CR3","doi-asserted-by":"publisher","unstructured":"Chandna, P., Ramires, A., Serra, X., G\u2019omez, E.: Loopnet: musical loop synthesis conditioned on intuitive musical parameters. In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3395\u20133399 (2021). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9415047","DOI":"10.1109\/ICASSP39728.2021.9415047"},{"key":"27_CR4","doi-asserted-by":"publisher","unstructured":"Devis, N., Demerl\u00e9, N., Nabi, S., Genova, D., Esling, P.: Continuous descriptor-based control for deep audio synthesis. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135 (2023). https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10096670","DOI":"10.1109\/ICASSP49357.2023.10096670"},{"key":"27_CR5","unstructured":"Donahue, C., McAuley, J., Puckette, M.: Adversarial audio synthesis (2018)"},{"key":"27_CR6","unstructured":"Engel, J., Agrawal, K.K., Chen, S., Gulrajani, I., Donahue, C., Roberts, A.: GANSynth: adversarial neural audio synthesis. In: International Conference on Learning Representations (2018)"},{"key":"27_CR7","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)"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Limberg, C., Zhang, Z.: Mapping the audio landscape for innovative music sample generation. In: ACM International Conference on Multimedia Retrieval (2024)","DOI":"10.1145\/3652583.3657586"},{"key":"27_CR9","doi-asserted-by":"publisher","unstructured":"Narita, G., Shimizu, J., Akama, T.: GANStrument: adversarial instrument sound synthesis with pitch-invariant instance conditioning. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135 (2023). https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10097250","DOI":"10.1109\/ICASSP49357.2023.10097250"},{"key":"27_CR10","unstructured":"Vaswani, A., et al.: Attention is all you need (2023)"},{"key":"27_CR11","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Akama, T.: HyperGANstrument: instrument sound synthesis and editing with pitch-invariant hypernetworks. In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6640\u20136644 (2024). https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10447847","DOI":"10.1109\/ICASSP48485.2024.10447847"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2074-6_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T17:20:30Z","timestamp":1779816030000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2074-6_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819620739","9789819620746"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2074-6_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"1 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}