{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T20:13:19Z","timestamp":1785010399101,"version":"3.55.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095926","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Textless Speech-to-Music Retrieval Using Emotion Similarity"],"prefix":"10.1109","author":[{"given":"SeungHeon","family":"Doh","sequence":"first","affiliation":[{"name":"KAIST,Graduate School of Culture Technology,South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minz","family":"Won","sequence":"additional","affiliation":[{"name":"ByteDance,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keunwoo","family":"Choi","sequence":"additional","affiliation":[{"name":"Gaudio Lab,South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juhan","family":"Nam","sequence":"additional","affiliation":[{"name":"KAIST,Graduate School of Culture Technology,South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWAMTIP51612.2020.9317379"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref15","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems NeurIPS"},{"key":"ref14","article-title":"Semi-supervised music tagging transformer","author":"won","year":"2021","journal-title":"Proceedings of International Society for Music Information Retrieval ISMIR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1852"},{"key":"ref10","article-title":"Exploring wav2vec 2.0 fine-tuning for improved speech emotion recognition","author":"chen","year":"2021","journal-title":"arXiv preprint arXiv 2110 07058"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206046"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1017"},{"key":"ref16","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"sanh","year":"2019","journal-title":"Neural Information Processing Systems Workshop on Energy Efficient Machine Learning and Cognitive Computing"},{"key":"ref19","article-title":"Learning a cross-domain embedding space of vocal and mixed audio with a structure-preserving triplet loss","author":"kim","year":"2021","journal-title":"Proceedings of International Society for Music Information Retrieval Conference ISMIR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980227"},{"key":"ref26","article-title":"Umap: Uniform manifold approximation and projection for dimension reduction","author":"mcinnes","year":"2018","journal-title":"arXiv preprint arXiv 1802 03426"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref8","article-title":"Transfer learning for music classification and regression tasks","author":"choi","year":"2017","journal-title":"Proceedings of International Society for Music Information Retrieval ISMIR"},{"key":"ref7","article-title":"RankSim: Ranking similarity regularization for deep imbalanced regression","author":"gong","year":"2022","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref9","article-title":"Codified audio language modeling learns useful representations for music information retrieval","author":"castellon","year":"2021","journal-title":"Proceedings of International Society for Music Information Retrieval Conference ISMIR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01031"},{"key":"ref3","article-title":"Query by video: Cross-modal music retrieval","author":"li","year":"2019","journal-title":"Proceedings of International Society for Music Information Retrieval ISMIR"},{"key":"ref6","article-title":"A comprehensive survey on cross-modal retrieval","author":"wang","year":"2016","journal-title":"arXiv preprint arXiv 1607 06215"},{"key":"ref5","article-title":"Emotion embedding spaces for matching music to stories","author":"won","year":"2021","journal-title":"Proceedings of International Society for Music Information Retrieval ISMIR"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095926.pdf?arnumber=10095926","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:00:22Z","timestamp":1700488822000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095926\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095926","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}