{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T11:41:34Z","timestamp":1767008494906,"version":"3.29.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T00:00:00Z","timestamp":1727827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T00:00:00Z","timestamp":1727827200000},"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":[[2024,10,2]]},"DOI":"10.1109\/mmsp61759.2024.10743615","type":"proceedings-article","created":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T18:35:35Z","timestamp":1731436535000},"page":"1-6","source":"Crossref","is-referenced-by-count":6,"title":["Exploiting Consistency-Preserving Loss and Perceptual Contrast Stretching to Boost SSL-Based Speech Enhancement"],"prefix":"10.1109","author":[{"given":"Muhammad Salman","family":"Khan","sequence":"first","affiliation":[{"name":"Kore University of Enna,Enna,Italy"}]},{"given":"Moreno La","family":"Quatra","sequence":"additional","affiliation":[{"name":"Kore University of Enna,Enna,Italy"}]},{"given":"Kuo-Hsuan","family":"Hung","sequence":"additional","affiliation":[{"name":"Academia Sinica,Taipei,China"}]},{"given":"Szu-Wei","family":"Fu","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation,Taipei,China"}]},{"given":"Sabato Marco","family":"Siniscalchi","sequence":"additional","affiliation":[{"name":"Università degli Studi di Palermo,Palermo,Italy"}]},{"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[{"name":"Academia Sinica,Taipei,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462581"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10839"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1864"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref6","first-page":"7","article-title":"A regression approach to speech enhancement based on deep neural networks","volume":"23.1","author":"Yong","year":"2014","journal-title":"IEEE\/ ACM transactions on audio, speech, and language processing"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3050386"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2821903"},{"key":"ref9","article-title":"Metricgan: Generative adversarial networks based black-box metric scores optimization for speech enhancement","volume-title":"International Conference on Machine Learning. PMLR","author":"Fu","year":"2019"},{"journal-title":"SEGAN: Speech enhancement generative adversarial network","year":"2017","author":"Santiago","key":"ref10"},{"journal-title":"Cmgan: Conformer-based metric gan for speech enhancement","year":"2022","author":"Ruizhe","key":"ref11"},{"journal-title":"SCP-GAN: Self-correcting discriminator optimization for training consistency pre-serving metric GAN on speech enhancement tasks","year":"2022","author":"Vasily","key":"ref12"},{"key":"ref13","first-page":"139","article-title":"Generative adversarial networks","volume":"63.11","author":"Ian","year":"2020","journal-title":"Communications of the ACM"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461530"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2291"},{"journal-title":"Auto-encoding variational bayes","year":"2013","author":"Kingma","key":"ref16"},{"key":"ref17","first-page":"6840","article-title":"Denoising diffusion proba-bilistic models","volume":"33","author":"Jonathan","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285241"},{"issue":"05","key":"ref20","article-title":"Phasen: A phase-and-harmonics-aware speech en-hancement network","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"34","author":"Dacheng","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1441"},{"key":"ref22","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Alexei","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref24","first-page":"1505","article-title":"Wavlm: Large-scale self-supervised pre-training for full stack speech processing","volume":"16.6","author":"Sanyuan","year":"2022","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10002"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023356"},{"journal-title":"Conformer: Convolution-augmented transformer for speech recognition","year":"2020","author":"Anmol","key":"ref28"},{"key":"ref29","article-title":"Conformer-based sound event detection with semi-supervised learning and data augmentation","volume":"1.4","author":"Koichi","year":"2020","journal-title":"dim"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413555"},{"key":"ref31","article-title":"SE-Conformer: Time-Domain Speech Enhancement Using Conformer","author":"Eesung","year":"2021","journal-title":"Interspeech"},{"key":"ref32","article-title":"Differentiable consistency constraints for im-proved deep speech enhancement","volume-title":"ICASSP 2019\u20132019 IEEE In-ternational Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE","author":"Scott","year":"2019"},{"journal-title":"Perceptual contrast stretching on target feature for speech enhancement","year":"2022","author":"Rong","key":"ref33"},{"key":"ref34","article-title":"Phase-aware speech enhancement with deep complex u-net","volume-title":"International Conference on Learning Representations","author":"Hyeong-Seok","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2548"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-24"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref40","first-page":"229","article-title":"Evaluation of objective quality mea-sures for speech enhancement","volume":"16.1","author":"Yi","year":"2007","journal-title":"IEEE Transactions on audio, speech, and language processing"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746303"},{"journal-title":"TridentSE: Guiding speech enhancement with 32 global tokens","year":"2022","author":"Dacheng","key":"ref43"},{"key":"ref44","article-title":"Boosting Speech Enhancement with Clean Self-Supervised Features Via Conditional Variational Au-toencoders","volume-title":"ICASSP 2024\u20132024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE","author":"Yoonhyung","year":"2024"}],"event":{"name":"2024 IEEE 26th International Workshop on Multimedia Signal Processing (MMSP)","start":{"date-parts":[[2024,10,2]]},"location":"West Lafayette, IN, USA","end":{"date-parts":[[2024,10,4]]}},"container-title":["2024 IEEE 26th International Workshop on Multimedia Signal Processing (MMSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10743173\/10743194\/10743615.pdf?arnumber=10743615","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T14:41:32Z","timestamp":1732718492000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10743615\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,2]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/mmsp61759.2024.10743615","relation":{},"subject":[],"published":{"date-parts":[[2024,10,2]]}}}