{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T05:07:55Z","timestamp":1737176875518,"version":"3.33.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"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":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10825221","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"3242-3247","source":"Crossref","is-referenced-by-count":0,"title":["Diffusion Models for Automatic Music Mixing"],"prefix":"10.1109","author":[{"given":"Xinyang","family":"Wu","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology,Dept. Computer Science and Engineering,Hong Kong"}]},{"given":"Andrew","family":"Horner","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,Dept. Computer Science and Engineering,Hong Kong"}]}],"member":"263","reference":[{"article-title":"Multitrack Mixing: An Investigation into Music Mixing Practices","year":"2018","author":"Tot","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/sj.bdj.4811337"},{"key":"ref3","first-page":"1","article-title":"Can we fx it? \u2013 The consequences of \u2018fxing it in the mix\u2019 with common equalisation techniques are scientifically evaluated","volume":"3","author":"Toulson","year":"2008","journal-title":"Journal of Artistic Recording and Production"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/9781119991298.ch1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/app10030791"},{"volume-title":"MUSDB18-HQ \u2013 An Uncompressed Version of MUSDB18","year":"2019","author":"Rafi","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096956"},{"article-title":"Hybrid Spectrogram and Waveform Source Separation","volume-title":"Proceedings of the ISMIR 2021 Workshop on Music Source Separation","author":"D\u00e9fossez","key":"ref8"},{"journal-title":"Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory","author":"Fu","key":"ref9"},{"journal-title":"A knowledge-engineered autonomous mixing system","year":"2013","author":"De Man","key":"ref10"},{"journal-title":"Towards an Automated Multitrack Mixing Tool using Answer Set Programming","year":"2017","author":"Everardo","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03754-2_2"},{"article-title":"Automatic music mixing with deep learning and out-of-domain data","year":"2022","author":"Mart\u00ednez-Ram\u00edrez","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683634"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09838-1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-022-00266-3"},{"article-title":"Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation","year":"2018","author":"Stoller","key":"ref17"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.17743\/jaes.2020.0031","article-title":"A Deep Learning Approach to Intelligent Drum Mixing With the Wave-U-Net","volume-title":"Centre for Digital Music","author":"Mart\u00ednez Ram\u00edrez","year":"2021"},{"article-title":"Denoising Diffusion Probabilistic Models","year":"2020","author":"Ho","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10653"},{"article-title":"Diffusion Models for Audio Restoration","year":"2024","author":"Lemercier","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.physrep.2007.05.006"},{"article-title":"Improving the performance of EEG decoding using anchored-STFT in conjunction with gradient norm adversarial augmentation","year":"2020","author":"Ali","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10444-010-9167-y"},{"article-title":"mir_eval: A Transparent Implementation of Common MIR Metrics","volume-title":"Proceedings of the 15th International Conference on Music Information Retrieval","author":"Raffel","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.1990.115972"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tasl.2013.2283105"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1017\/9781108644198.014","article-title":"Measuring Speech. Fundamental frequency and pitch","volume-title":"Cambridge Handbook of Phonetics","author":"Hirst","year":"2021"},{"issue":"19","key":"ref29","first-page":"3229","article-title":"Universal and Non-universal Features of Musical Pitch Perception Revealed by Singing","volume-title":"Current Biology","volume":"29","author":"Jacoby","year":"2019"},{"key":"ref30","first-page":"1","article-title":"An Attention-Based Improved U-Net Neural Network Model for Semantic Segmentation of Moving Objects","volume-title":"IEEE Access","volume":"PP","author":"Cui","year":"2024"},{"key":"ref31","first-page":"8589","article-title":"Improved UNet with Attention for Medical Image Segmentation","volume-title":"Sensors","volume":"23","author":"Al Qurri","year":"2023"},{"key":"ref32","first-page":"1406","article-title":"Complex-Valued Neural Networks: A Comprehensive Survey","volume-title":"IEEE\/CAA Journal of Automatica Sinica","volume":"9","author":"Lee","year":"2022"},{"article-title":"Deep Residual Learning for Image Recognition","year":"2015","author":"He","key":"ref33"},{"article-title":"The Disappearance of Timestep Embedding in Modern Time-Dependent Neural Networks","year":"2024","author":"Kim","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2190279"},{"key":"ref37","first-page":"1","article-title":"Phase Retrieval: Application to Audio Signal Reconstruction","volume-title":"Proceedings of the 2022 International Multi-Conference on Systems, Signals & Devices (SSD)","author":"Bedoui"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","start":{"date-parts":[[2024,12,15]]},"location":"Washington, DC, USA","end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10825221.pdf?arnumber=10825221","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:54:24Z","timestamp":1737100464000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10825221\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10825221","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}