{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:43:05Z","timestamp":1777657385507,"version":"3.51.4"},"reference-count":33,"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\/icassp49357.2023.10095132","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":5,"title":["Efficient Speech Quality Assessment Using Self-Supervised Framewise Embeddings"],"prefix":"10.1109","author":[{"given":"Karl","family":"El Hajal","sequence":"first","affiliation":[{"name":"École Polytechnique Fédérale de Lausanne (EPFL),Lausanne,Switzerland"}]},{"given":"Zihan","family":"Wu","sequence":"additional","affiliation":[{"name":"École Polytechnique Fédérale de Lausanne (EPFL),Lausanne,Switzerland"}]},{"given":"Neil","family":"Scheidwasser-Clow","sequence":"additional","affiliation":[{"name":"University of Copenhagen,Copenhagen,Denmark"}]},{"given":"Gasser","family":"Elbanna","sequence":"additional","affiliation":[{"name":"École Polytechnique Fédérale de Lausanne (EPFL),Lausanne,Switzerland"}]},{"given":"Milos","family":"Cernak","sequence":"additional","affiliation":[{"name":"Logitech Europe,Lausanne,Switzerland"}]}],"member":"263","reference":[{"key":"ref13","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref12","first-page":"2278","article-title":"XLS-R: Self-supervised cross-lingual speech representation learning at scale","author":"babu","year":"2021","journal-title":"InterSpeech"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747348"},{"key":"ref14","article-title":"Wav2vec2. 0 on the edge: Performance evaluation","author":"gondi","year":"2022"},{"key":"ref31","article-title":"The efficiency misnomer","author":"dehghani","year":"2022","journal-title":"ICLRE"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2760"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10147"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-659"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10597"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414052"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937202"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683175"},{"key":"ref17","first-page":"125","article-title":"HEAR: Holistic Evaluation of Audio Representations","author":"turian","year":"2022","journal-title":"NeurIPS Competitions and Demonstrations Track"},{"key":"ref16","article-title":"BYOL-S: Learning self-supervised speech representations by bootstrapping","author":"elbanna","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10498"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10698"},{"key":"ref24","first-page":"1459","article-title":"openSMILE - The Munich Versatile and Fast Open-Source Audio Feature Extractor","author":"eyben","year":"2010","journal-title":"Proc ACM Multimedia (MM)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref26","article-title":"P.Sup23 : ITU-T coded-speech database","year":"1998"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534474"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref21","first-page":"21271","article-title":"Bootstrap your own latent - a new approach to self-supervised learning","author":"grill","year":"2020","journal-title":"NeurIPS"},{"key":"ref28","first-page":"2406","article-title":"NonIntrusive Speech Quality Assessment with Transfer Learning and Subject-Specific Scaling","author":"nessler","year":"2021","journal-title":"InterSpeech"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2015.7148100"},{"key":"ref29","first-page":"356","article-title":"A Universal Deep Room Acoustics Estimator","author":"l?pez","year":"2021","journal-title":"WASPAA"},{"key":"ref8","first-page":"196","article-title":"CD-PAM: Contrastive learning for perceptual audio similarity","author":"manocha","year":"2021","journal-title":"ICASSP"},{"key":"ref7","first-page":"749","article-title":"Perceptual evaluation of speech quality (PESQ)","volume":"2","author":"rix","year":"2001","journal-title":"ICASSP"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19551-8_23"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683770"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1802"},{"key":"ref6","first-page":"22363","article-title":"NORESQA: A framework for speech quality assessment using non-matching references","volume":"34","author":"manocha","year":"2021","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"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\/10095132.pdf?arnumber=10095132","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T23:05:01Z","timestamp":1698102301000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095132\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095132","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}