{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T23:10:21Z","timestamp":1765667421010,"version":"3.40.3"},"publisher-location":"Cham","reference-count":39,"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_11","type":"book-chapter","created":{"date-parts":[[2023,4,4]],"date-time":"2023-04-04T23:03:58Z","timestamp":1680649438000},"page":"164-179","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["SketchSynth: Cross-Modal Control of\u00a0Sound Synthesis"],"prefix":"10.1007","author":[{"given":"Sebastian","family":"L\u00f6bbers","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Louise","family":"Thorpe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gy\u00f6rgy","family":"Fazekas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,1]]},"reference":[{"key":"11_CR1","doi-asserted-by":"publisher","first-page":"352","DOI":"10.3389\/fnhum.2014.00352","volume":"8","author":"M Adeli","year":"2014","unstructured":"Adeli, M., Rouat, J., Molotchnikoff, S.: Audiovisual correspondence between musical timbre and visual shapes. Front. Hum. Neurosci. 8, 352 (2014). https:\/\/doi.org\/10.3389\/fnhum.2014.00352","journal-title":"Front. Hum. Neurosci."},{"key":"11_CR2","doi-asserted-by":"publisher","unstructured":"Bottini, R., Barilari, M., Collignon, O.: Sound symbolism in sighted and blind. the role of vision and orthography in sound-shape correspondences. Cognition 185, 62\u201370 (2019). https:\/\/doi.org\/10.1016\/j.cognition.2019.01.006","DOI":"10.1016\/j.cognition.2019.01.006"},{"issue":"2","key":"11_CR3","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1191\/1478088706qp063oa","volume":"3","author":"V Braun","year":"2006","unstructured":"Braun, V., Clarke, V.: Using thematic analysis in psychology. Qual. Res. Psychol. 3(2), 77\u2013101 (2006). https:\/\/doi.org\/10.1191\/1478088706qp063oa","journal-title":"Qual. Res. Psychol."},{"key":"11_CR4","unstructured":"Bruford, F., Barthet, M., McDonald, S., Sandler, M.B.: Groove explorer: An intelligent visual interface for drum loop library navigation. In: Proceedings of the ACM IUI Workshops. CEUR-WS.org, Los Angeles, USA (2019)"},{"issue":"1841","key":"11_CR5","doi-asserted-by":"publisher","first-page":"20200390","DOI":"10.1098\/rstb.2020.0390","volume":"377","author":"A \u0106wiek","year":"2022","unstructured":"\u0106wiek, A., et al.: The Bouba\/Kiki effect is robust across cultures and writing systems. Philosop. Trans. Royal Soc. B: Biol. Sci. 377(1841), 20200390 (2022). https:\/\/doi.org\/10.1098\/rstb.2020.0390","journal-title":"Philosop. Trans. Royal Soc. B: Biol. Sci."},{"key":"11_CR6","unstructured":"Das, A., Yang, Y., Hospedales, T., Xiang, T., Song, Y.Z.: SketchODE: learning neural sketch representation in continuous time. In: Proceedings of International Conference on Learning Representations. OpenReview.net, virtual (2022)"},{"key":"11_CR7","unstructured":"De Man, B., Reiss, J., Stables, R.: Ten years of automatic mixing. In: Proceedings of the Workshop on Intelligent Music Production. Salford, U.K. (2017)"},{"issue":"6","key":"11_CR8","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","volume":"29","author":"L Deng","year":"2012","unstructured":"Deng, L.: The MNIST database of handwritten digit images for machine learning research. IEEE Signal Process. Mag. 29(6), 141\u2013142 (2012). https:\/\/doi.org\/10.1109\/MSP.2012.2211477","journal-title":"IEEE Signal Process. Mag."},{"issue":"4","key":"11_CR9","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1007\/s00779-020-01392-5","volume":"25","author":"L Engeln","year":"2020","unstructured":"Engeln, L., Groh, R.: CoHEARence of audible shapes\u2014a qualitative user study for coherent visual audio design with resynthesized shapes. Pers. Ubiquit. Comput. 25(4), 651\u2013661 (2020). https:\/\/doi.org\/10.1007\/s00779-020-01392-5","journal-title":"Pers. Ubiquit. Comput."},{"key":"11_CR10","doi-asserted-by":"publisher","unstructured":"Engeln, L., Le, N.L., McGinity, M., Groh, R.: Similarity analysis of visual sketch-based search for sounds. In: Proceedings of Audio Mostly 2021, pp. 101\u2013108. Association for Computing Machinery, Trento, Italy (2021). https:\/\/doi.org\/10.1145\/3478384.3478423","DOI":"10.1145\/3478384.3478423"},{"key":"11_CR11","doi-asserted-by":"publisher","unstructured":"Esling, P., Masuda, N., Chemla-Romeu-Santos, A.: FlowSynth: simplifying complex audio generation through explorable latent spaces with normalizing flows. In: Proceedings of International Joint Conference on Artificial Intelligence, pp. 5273\u20135275 (2020). https:\/\/doi.org\/10.24963\/ijcai.2020\/767","DOI":"10.24963\/ijcai.2020\/767"},{"key":"11_CR12","unstructured":"Garber, L., y Ciencia, M.A., Ciccola, T., Amusategui, J.C.: AudioStellar, an open source corpus-based musical instrument for latent sound structure discovery and sonic experimentation. In: Proceedings of International Computer Music Conference, pp. 86\u201391. Santiago, Chile (2021). https:\/\/hdl.handle.net\/2027\/fulcrum.t435gg568"},{"key":"11_CR13","unstructured":"Giannakis, K.: Sound mosaics: a graphical user interface for sound synthesis based on audio-visual associations, Ph. D. thesis, Middlesex University (2001)"},{"key":"11_CR14","unstructured":"Google: Quick, Draw! (2017). https:\/\/quickdraw.withgoogle.com\/. Accessed 8 Feb 2023"},{"key":"11_CR15","unstructured":"Grill, T., Flexer, A.: Visualization of Perceptual Qualities in Textural Sounds. In: Proceedings of International Computer Music Conference, pp. 589\u2013596. Michigan Publishing Services, Ljubljana, Slovenia (2012). http:\/\/hdl.handle.net\/2027\/spo.bbp2372.2012.110"},{"key":"11_CR16","unstructured":"Ha, D., Eck, D.: A neural representation of sketch drawings. arXiv preprint arXiv:1704.03477 (2017)"},{"key":"11_CR17","unstructured":"Hayes, B.: FM synth study (2020). https:\/\/github.com\/ben-hayes\/fm-synth-study. Accessed 8 Feb 2023"},{"key":"11_CR18","unstructured":"Hayes, B., Saitis, C.: There\u2019s more to timbre than musical instruments: semantic dimensions of FM sounds. In: Proceedings of International Conference on Timbre. Timbre 2020, Thessaloniki, Greece (2020)"},{"key":"11_CR19","doi-asserted-by":"publisher","unstructured":"Hayes, B., Saitis, C., Fazekas, G.: Disembodied timbres: a study on semantically prompted fm synthesis. J. Audio Eng. Soc. 70(5), 373\u2013391 (2022). https:\/\/doi.org\/10.17743\/jaes.2022.0006","DOI":"10.17743\/jaes.2022.0006"},{"key":"11_CR20","unstructured":"ISMIR: Homepage (2022). https:\/\/ismir.net\/. Accessed 8 Feb 2023"},{"key":"11_CR21","unstructured":"iZotope: Mix & Master Bundle Advanced (2023). https:\/\/www.izotope.com\/en\/shop\/mix-master-bundle-advanced.html. Accessed 8 Feb 2023"},{"key":"11_CR22","doi-asserted-by":"publisher","unstructured":"Knees, P., Andersen, K.: Searching for audio by sketching mental images of sound: a brave new idea for audio retrieval in creative music production. In: Proceedings of International Conference on Multimedia Retrieval, pp. 95\u2013102. Association for Computing Machinery, New York, USA (2016). https:\/\/doi.org\/10.1145\/2911996.2912021","DOI":"10.1145\/2911996.2912021"},{"key":"11_CR23","unstructured":"K\u00f6hler, W.: Gestalt psychology. Liveright (1929)"},{"key":"11_CR24","doi-asserted-by":"publisher","unstructured":"K\u00fcssner, M.B., Tidhar, D., Prior, H.M., Leech-Wilkinson, D.: Musicians are more consistent: gestural cross-modal mappings of pitch, loudness and tempo in real-time. Front. Psychol. 5, 00789 (2014). https:\/\/doi.org\/10.3389\/fpsyg.2014.00789","DOI":"10.3389\/fpsyg.2014.00789"},{"key":"11_CR25","unstructured":"L\u00f6bbers, S., Barthet, M., Fazekas, G.: Sketching sounds: an exploratory study on sound-shape associations. In: Proceedings of International Computer Music Conference, pp. 299\u2013304. Michigan Publishing Services, Santiago, Chile (2021). https:\/\/hdl.handle.net\/2027\/fulcrum.t435gg568"},{"key":"11_CR26","unstructured":"L\u00f6bbers, S., Fazekas, G.: Seeing sounds, hearing shapes: a gamified study to evaluate sound-sketches. In: Proceedings International Computer Music Conference, pp. 174\u2013179. Michigan Publishing Services, Limerick, Ireland (2022). https:\/\/hdl.handle.net\/2027\/fulcrum.nk322g689"},{"key":"11_CR27","doi-asserted-by":"publisher","unstructured":"L\u00f6bbers, S., Fazekas, G.: Sketching Sounds Dataset (1.0) [Data set] (2023). https:\/\/doi.org\/10.5281\/zenodo.7590916","DOI":"10.5281\/zenodo.7590916"},{"key":"11_CR28","doi-asserted-by":"publisher","unstructured":"L\u00f6bbers, S., Fazekas, G.: SketchSynth Dataset (1.0) [Data set] (2023). https:\/\/doi.org\/10.5281\/zenodo.7591067","DOI":"10.5281\/zenodo.7591067"},{"issue":"2","key":"11_CR29","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1111\/1467-8721.00116","volume":"10","author":"G Martino","year":"2001","unstructured":"Martino, G., Marks, L.E.: Synesthesia: strong and weak. Curr. Dir. Psychol. Sci. 10(2), 61\u201365 (2001)","journal-title":"Curr. Dir. Psychol. Sci."},{"issue":"2","key":"11_CR30","doi-asserted-by":"publisher","first-page":"783","DOI":"10.1121\/1.4974825","volume":"141","author":"A Mehrabi","year":"2017","unstructured":"Mehrabi, A., Dixon, S., Sandler, M.B.: Vocal imitation of synthesised sounds varying in pitch, loudness and spectral centroid. J. Acoust. Soc. Am. 141(2), 783\u2013796 (2017)","journal-title":"J. Acoust. Soc. Am."},{"key":"11_CR31","doi-asserted-by":"publisher","unstructured":"Moffat, D., Sandler, M.B.: Approaches in intelligent music production. Arts 8(4), 125 (2019). https:\/\/doi.org\/10.3390\/arts8040125","DOI":"10.3390\/arts8040125"},{"issue":"12","key":"11_CR32","first-page":"3","volume":"8","author":"VS Ramachandran","year":"2001","unstructured":"Ramachandran, V.S., Hubbard, E.M.: Synaesthesia-a window into perception, thought and language. J. Conscious. Stud. 8(12), 3\u201334 (2001)","journal-title":"J. Conscious. Stud."},{"key":"11_CR33","unstructured":"Sezgin, T.M.: Feature point detection and curve approximation for early processing of free-hand sketches, Ph. D. thesis, Massachusetts Institute of Technology (2001)"},{"key":"11_CR34","doi-asserted-by":"publisher","unstructured":"Singh, S., Bromham, G., Sheng, D., Fazekas, G.: Intelligent control method for the dynamic range compressor: a user study. J. Audio Eng. Soc. 69(7\/8), 576\u2013585 (2021). https:\/\/doi.org\/10.17743\/jaes.2021.0028","DOI":"10.17743\/jaes.2021.0028"},{"key":"11_CR35","doi-asserted-by":"publisher","unstructured":"Wolin, A., Eoff, B., Hammond, T.: ShortStraw: a simple and effective corner finder for polylines. In: Proceedings of Eurographics Workshop on Sketch-Based Interfaces and Modeling. The Eurographics Association, Annecy, France (2008). https:\/\/doi.org\/10.2312\/SBM\/SBM08\/033-040","DOI":"10.2312\/SBM\/SBM08\/033-040"},{"key":"11_CR36","doi-asserted-by":"publisher","unstructured":"Xiong, Y., LaViola, J.J.: Revisiting shortStraw: improving corner finding in sketch-based interfaces. In: Proceedings of Eurographics Symposium on Sketch-Based Interfaces and Modeling, pp. 101\u2013108. Association for Computing Machinery, New Orleans USA (2009). https:\/\/doi.org\/10.2312\/SBM\/SBM09\/101-108","DOI":"10.2312\/SBM\/SBM09\/101-108"},{"key":"11_CR37","unstructured":"XLN Audio: XO product page (2023). https:\/\/www.xlnaudio.com\/products\/xo. Accessed 8 Feb 2023"},{"key":"11_CR38","doi-asserted-by":"crossref","unstructured":"Xu, P., et al.: SketchMate: deep hashing for million-scale human sketch retrieval. In: Proceedings of Conference on Computer Vision and Pattern Recognition, pp. 8090\u20138098. IEEE Computer Society, Salt Lake City, USA (2018)","DOI":"10.1109\/CVPR.2018.00844"},{"key":"11_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1007\/978-3-030-70210-6_39","volume-title":"Perception, Representations, Image, Sound, Music","author":"M Zbyszy\u0144ski","year":"2021","unstructured":"Zbyszy\u0144ski, M., Di Donato, B., Visi, F.G., Tanaka, A.: Gesture-timbre space: multidimensional feature mapping using machine learning and concatenative synthesis. In: Kronland-Martinet, R., Ystad, S., Aramaki, M. (eds.) CMMR 2019. LNCS, vol. 12631, pp. 600\u2013622. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-70210-6_39"}],"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_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T19:43:08Z","timestamp":1710358988000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-29956-8_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031299551","9783031299568"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-29956-8_11","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)"}}]}}