{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:51:27Z","timestamp":1764399087241,"version":"3.46.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249148","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"270-275","source":"Crossref","is-referenced-by-count":0,"title":["Unified Timbre Transfer: A Compact Model for Real-Time Multi-Instrument Sound Morphing"],"prefix":"10.1109","author":[{"given":"Anders R.","family":"Bargum","sequence":"first","affiliation":[{"name":"Aalborg University,Multisensory Experience Lab,Copenhagen,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naotake","family":"Masuda","sequence":"additional","affiliation":[{"name":"Qosmo & Neutone AI,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bogdan","family":"Teleaga","sequence":"additional","affiliation":[{"name":"Qosmo & Neutone AI,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Fyfe","sequence":"additional","affiliation":[{"name":"Qosmo & Neutone AI,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cumhur","family":"Erkut","sequence":"additional","affiliation":[{"name":"Aalborg University,Multisensory Experience Lab,Copenhagen,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"WaveNet: A generative model for raw audio","year":"2016","author":"Oord","key":"ref1"},{"key":"ref2","article-title":"Neural audio synthesis of musical notes with WaveNet autoencoders","volume-title":"Proceedings of the 34th International Conference on Machine Learning","author":"Engel","year":"2017"},{"key":"ref3","volume-title":"RAVE: A variational autoencoder for fast and high-quality neural audio synthesis","volume":"abs\/2111.05011","author":"Caillon","year":"2021"},{"volume-title":"Stable audio open","year":"2024","author":"Evans","key":"ref4"},{"key":"ref5","article-title":"DDSP: Differentiable digital signal processing","volume-title":"International Conference on Learning Representations","author":"Engel","year":"2020"},{"key":"ref6","first-page":"47704","article-title":"Simple and controllable music generation","author":"Copet","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414235"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096670"},{"key":"ref9","first-page":"383","article-title":"P-RAVE: Improving RAVE through pitch conditioning and more with application to singing voice conversion","volume-title":"Proc. Intl. Conf. on Digital Audio Effects","author":"Nercessian","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref11","article-title":"DDSP-based singing vocoders: A new subtractive-based synthesizer and a comprehensive evaluation.","author":"Wu","year":"2022","journal-title":"ISMIR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683596"},{"key":"ref13","article-title":"Combining audio control and style transfer using latent diffusion","volume-title":"Proc. of the 25th Int. Society for Music Information Retrieval Conf.","author":"Demerle","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902701"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1121\/1.1458024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2815"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"volume-title":"TokenSynth: A token-based neural synthesizer for instrument cloning and text-to-instrument","year":"2025","author":"Kim","key":"ref18"},{"key":"ref19","article-title":"Generative timbre spaces: Regularizing variational auto-encoders with perceptual metrics","volume-title":"Proc. Intl. Conf. on Digital Audio Effects","author":"Esling","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1121\/1.381843"},{"volume-title":"Crossdomain neural pitch and periodicity estimation","year":"2023","author":"Morrison","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2856090"},{"journal-title":"The chamber ensemble generator: Limitless high-quality MIR data via generative modeling","year":"2022","author":"Wu","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892107"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746549"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"},{"key":"ref27","first-page":"723","article-title":"A kernel two-sample test","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res."}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249148.pdf?arnumber=11249148","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:50:31Z","timestamp":1764399031000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249148\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249148","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}