{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:19:14Z","timestamp":1774419554599,"version":"3.50.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889579","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["D3RM: A Discrete Denoising Diffusion Refinement Model for Piano Transcription"],"prefix":"10.1109","author":[{"given":"Hounsu","family":"Kim","sequence":"first","affiliation":[{"name":"Graduate School of Culture Technology KAIST,Daejeon,South Korea"}]},{"given":"Taegyun","family":"Kwon","sequence":"additional","affiliation":[{"name":"Graduate School of Culture Technology KAIST,Daejeon,South Korea"}]},{"given":"Juhan","family":"Nam","sequence":"additional","affiliation":[{"name":"Graduate School of Culture Technology KAIST,Daejeon,South Korea"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Automatic piano transcription with hierarchical frequency-time transformer","volume-title":"Proc. of the 24th International Society for Music Information Retrieval Conference (ISMIR)","author":"Toyama"},{"key":"ref2","article-title":"Scoring intervals using non-hierarchical transformer for automatic piano transcription","author":"Yan","year":"2024"},{"key":"ref3","article-title":"Naturalspeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","author":"Ju","year":"2024"},{"key":"ref4","article-title":"Analog bits: Generating discrete data using diffusion models with self-conditioning","volume-title":"The Eleventh International Conference on Learning Representations","author":"Chen"},{"key":"ref5","article-title":"Dformer: Diffusion-guided transformer for universal image segmentation","author":"Wang","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095935"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"ref8","first-page":"50","article-title":"Onsets and frames: Dual-objective piano transcription","volume-title":"Proc. of the 19th International Society for Music Information Retrieval Conference (ISMIR)","author":"Hawthorne"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3121991"},{"key":"ref10","first-page":"709","article-title":"Hppnet: Modeling the harmonic structure and pitch invariance in piano transcription","volume-title":"Proceedings of the 23rd International Society for Music Information Retrieval Conference, ISMIR 2022, Bengaluru, India, December 4-8, 2022","author":"Wei"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3507568"},{"key":"ref12","article-title":"Sequence-to-sequence piano transcription with transformers","volume-title":"Proc. of the 22th International Society for Music Information Retrieval Conference (ISMIR)","author":"Hawthorne"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447324"},{"key":"ref14","article-title":"Polyphonic piano transcription using autoregressive multi-state note model","volume-title":"International Society for Music Information Retrieval Conference","author":"Kwon"},{"key":"ref15","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2020"},{"key":"ref16","article-title":"Wavenet: A generative model for raw audio","author":"Oord","year":"2016"},{"key":"ref17","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International Conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref18","first-page":"12454","article-title":"Argmax flows and multinomial diffusion: Learning categorical distributions","volume":"34","author":"Hoogeboom","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","first-page":"17981","article-title":"Structured denoising diffusion models in discrete state-spaces","volume":"34","author":"Austin","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref22","article-title":"Enabling factorized piano music modeling and generation with the MAESTRO dataset","volume-title":"International Conference on Learning Representations","author":"Hawthorne"},{"key":"ref23","first-page":"367","article-title":"mir_eval: A transparent implementation of common MIR metrics","volume-title":"Proc. of the 15th International Society for Music Information Retrieval Conference (ISMIR)","author":"Raffel"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889579.pdf?arnumber=10889579","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:29Z","timestamp":1774416209000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889579\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889579","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}