{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:32:34Z","timestamp":1763202754754,"version":"3.28.0"},"reference-count":39,"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\/icassp49357.2023.10095596","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":6,"title":["Self-Remixing: Unsupervised Speech Separation VIA Separation and Remixing"],"prefix":"10.1109","author":[{"given":"Kohei","family":"Saijo","sequence":"first","affiliation":[{"name":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan"}]},{"given":"Tetsuji","family":"Ogawa","sequence":"additional","affiliation":[{"name":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747463"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747473"},{"key":"ref12","first-page":"5318","article-title":"Speaker-Aware Mixture of Mixtures Training for Weakly Supervised Speaker Extraction","author":"zhao","year":"2021","journal-title":"Proc INTERSPEECH"},{"key":"ref34","first-page":"626","article-title":"Sdr– half-baked or well done?","author":"le roux","year":"2021","journal-title":"Proc ICASSP"},{"key":"ref15","article-title":"Unsupervised source separation via self-supervised training","author":"karamatl?","year":"2022","journal-title":"arXiv preprint arXiv 2202 03875"},{"key":"ref37","first-page":"749","article-title":"Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs","volume":"2","author":"rix","year":"2021","journal-title":"Proc ICASSP"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3200911"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref31","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2021","journal-title":"Proc ICLR"},{"key":"ref30","first-page":"3","article-title":"Group normalization","author":"wu","year":"2021","journal-title":"Proc ECCV"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1243"},{"key":"ref33","first-page":"236","article-title":"Independence-based joint dereverberation and separation with neural source model","author":"saijo","year":"2021","journal-title":"Proc INTERSPEECH"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747855"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_27"},{"key":"ref2","first-page":"351","article-title":"Pyroomacoustics: A python package for audio room simulation and array processing algorithms","author":"scheibler","year":"2021","journal-title":"Proc ICASSP"},{"key":"ref1","first-page":"241","article-title":"Permutation invariant training of deep models for speaker-independent multi-talker speech separation","author":"yu","year":"2021","journal-title":"Proc ICASSP"},{"key":"ref17","article-title":"Remix-cycle-consistent learning on adversarially learned separator for accurate and stable unsupervised speech separation","author":"saijo","year":"2021","journal-title":"Proc ICASSP"},{"key":"ref39","first-page":"175","article-title":"Universal sound separation","author":"kavalerov","year":"2021","journal-title":"Proc WASPAA"},{"key":"ref16","first-page":"3272","article-title":"Towards unsupervised single-channel blind source separation using adversarial pair unmix-and-remix","author":"hoshen","year":"2021","journal-title":"Proc ICASSP"},{"key":"ref38","first-page":"28","article-title":"The ami meeting corpus: A pre-announcement","author":"carletta","year":"2005","journal-title":"Int Workshop Mach Learn Multimodal Interact"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682783"},{"key":"ref18","first-page":"251","article-title":"Unsupervised training of sequential neural beamformer using coarsely-separated and non-separated signals","author":"saijo","year":"2021","journal-title":"Proc INTERSPEECH"},{"key":"ref24","first-page":"7284","article-title":"Continuous speech separation: Dataset and analysis","author":"chen","year":"2021","journal-title":"Proc ICASSP"},{"key":"ref23","article-title":"Sms-wsj: Database, performance measures, and baseline recipe for multi-channel source separation and recognition","author":"drude","year":"2019","journal-title":"arXiv preprint arXiv 1910 13038"},{"key":"ref26","first-page":"2207","article-title":"ESPnet: End-toend speech processing toolkit","author":"watanabe","year":"2021","journal-title":"Proc INTERSPEECH"},{"key":"ref25","first-page":"5206","article-title":"Librispeech: An asr corpus based on public domain audio books","author":"panayotov","year":"2021","journal-title":"Proc ICASSP"},{"journal-title":"CSR-I (WSJ0) Complete LDC93S6A","year":"1993","author":"garofolo","key":"ref20"},{"key":"ref22","first-page":"504","article-title":"The third ‘CHiME’ speech separation and recognition challenge: Dataset, task and baselines","author":"barker","year":"2021","journal-title":"Proc ASRU"},{"journal-title":"CSR-II (WSJ1) Complete","year":"1994","key":"ref21"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413423"},{"key":"ref27","first-page":"5036","article-title":"Conformer: Convolution-augmented Transformer for Speech Recognition","author":"gulati","year":"2021","journal-title":"Proc INTERSPEECH"},{"key":"ref29","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2021","journal-title":"Proc ICML"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632714"},{"key":"ref7","first-page":"3846","article-title":"Unsupervised sound separation using mixture invariant training","volume":"33","author":"wisdom","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref9","first-page":"636","article-title":"Improving bird classification with unsupervised sound separation","author":"denton","year":"2021","journal-title":"Proc ICASSP"},{"key":"ref4","first-page":"695","article-title":"Unsupervised training of a deep clustering model for multichannel blind source separation","author":"drude","year":"2021","journal-title":"Proc ICASSP"},{"key":"ref3","first-page":"81","article-title":"Unsupervised deep clustering for source separation: Direct learning from mixtures using spatial information","author":"tzinis","year":"2021","journal-title":"Proc ICASSP"},{"key":"ref6","first-page":"241","article-title":"Spatial loss for unsupervised multichannel source separation","author":"saijo","year":"2021","journal-title":"Proc INTERSPEECH"},{"key":"ref5","first-page":"56","article-title":"Unsupervised training for deep speech source separation with kullback-leibler divergence based probabilistic loss function","author":"togami","year":"2021","journal-title":"Proc ICASSP"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","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\/10095596.pdf?arnumber=10095596","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:03:18Z","timestamp":1699902198000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095596\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095596","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}