{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T07:03:55Z","timestamp":1760598235417,"version":"3.37.3"},"reference-count":30,"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"}],"funder":[{"DOI":"10.13039\/100014013","name":"UK Research and Innovation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018696","name":"Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018696","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095666","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":8,"title":["Perceive and Predict: Self-Supervised Speech Representation Based Loss Functions for Speech Enhancement"],"prefix":"10.1109","author":[{"given":"George","family":"Close","sequence":"first","affiliation":[{"name":"University of Sheffield,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William","family":"Ravenscroft","sequence":"additional","affiliation":[{"name":"University of Sheffield,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Hain","sequence":"additional","affiliation":[{"name":"University of Sheffield,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Goetze","sequence":"additional","affiliation":[{"name":"University of Sheffield,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"journal-title":"Hubert Self-supervised speech representation learning by masked prediction of hidden units","year":"2021","author":"hsu","key":"ref12"},{"journal-title":"A systematic comparison of phonetic aware techniques for speech enhancement","year":"2022","author":"tal","key":"ref15"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3389\/frsip.2022.856968"},{"key":"ref11","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"0","journal-title":"Advances in neural information processing systems"},{"journal-title":"Metricgan-u Unsupervised speech enhancement\/ dereverberation based only on noisy\/ reverberated speech","year":"2021","author":"fu","key":"ref10"},{"journal-title":"MetricGAN+ An improved version of MetricGAN for speech enhancement","year":"2021","author":"fu","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3018668"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2821903"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10147"},{"key":"ref19","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc of ACL 2019"},{"journal-title":"DEMAND a collection of multi-channel recordings of acoustic noise in diverse environments","year":"2013","author":"thiemann","key":"ref24"},{"journal-title":"Noisy speech database for training speech enhancement algorithms and tts models","year":"2017","author":"valentini-botinhao","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2018.10.002"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"journal-title":"Improving perceptual quality by phone-fortified perceptual loss using wasserstein distance for speech enhancement","year":"2020","author":"hsieh","key":"ref22"},{"journal-title":"Conferencingspeech 2022 challenge Non-intrusive objective speech quality assessment (nisqa) challenge for online conferencing applications","year":"2022","author":"yi","key":"ref21"},{"journal-title":"Adam A method for stochastic optimization","year":"2017","author":"kingma","key":"ref28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"journal-title":"SpeechBrain A General-Purpose Speech Toolkit","year":"2021","author":"ravanelli","key":"ref29"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003986"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053327"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2968738"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909682"}],"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\/10095666.pdf?arnumber=10095666","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T18:56:26Z","timestamp":1699901786000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095666\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095666","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}