{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T20:23:40Z","timestamp":1790713420944,"version":"4.1.0"},"reference-count":26,"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\/icasspw59220.2023.10193042","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:54Z","timestamp":1690997454000},"page":"1-5","source":"Crossref","is-referenced-by-count":15,"title":["Fine-Tuning Strategies for Faster Inference Using Speech Self-Supervised Models: A Comparative Study"],"prefix":"10.1109","author":[{"given":"Salah","family":"Zaiem","sequence":"first","affiliation":[{"name":"Telecom Paris,Palaiseau,France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robin","family":"Algayres","sequence":"additional","affiliation":[{"name":"PSL Research University,ENS, INRIA, INSERM, UPEC,France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Titouan","family":"Parcollet","sequence":"additional","affiliation":[{"name":"Samsung AI Center,Cambridge,United-Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Slim","family":"Essid","sequence":"additional","affiliation":[{"name":"Telecom Paris,Palaiseau,France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mirco","family":"Ravanelli","sequence":"additional","affiliation":[{"name":"Mila-Quebec AI Institute, Université de Montréal, Concordia University,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","author":"radford","year":"2022","journal-title":"Robust speech recognition via large-scale weak supervision"},{"key":"ref12","article-title":"Efficient speech representation learning with low-bit quantization","author":"yeh","year":"2022","journal-title":"arXiv preprint arXiv 2301 07898"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022724"},{"key":"ref14","article-title":"Speechbrain: A general-purpose speech toolkit","author":"ravanelli","year":"2021","journal-title":"arXiv preprint arXiv 2106 04427"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022770"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11112"},{"key":"ref2","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","author":"chiu","year":"2022","journal-title":"International Conference on Machine Learning"},{"key":"ref1","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":"Advances in neural information processing systems"},{"key":"ref17","author":"graves","year":"2006","journal-title":"Connectionist temporal classification labelling unsegmented sequence data with recurrent neural networks"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639038"},{"key":"ref18","article-title":"KenLM: Faster and smaller language model queries","author":"heafield","year":"2011","journal-title":"Proceedings of the Sixth Workshop on Statistical Machine Translation"},{"key":"ref24","article-title":"Hubert-ee: Early exiting hubert for efficient speech recognition","author":"yoon","year":"2022","journal-title":"arXiv preprint arXiv 2204 06328"},{"key":"ref23","article-title":"Avoid overthinking in self-supervised models for speech recognition","author":"berrebbi","year":"2022","journal-title":"arXiv preprint arXiv 2211 08989"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.09.001"},{"key":"ref25","article-title":"The design for the Wall Street Journal-based CSR corpus","author":"paul","year":"1992","journal-title":"Speech and Natural Language Proceedings of a Workshop Held at Harriman"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref22","article-title":"Reducing transformer depth on demand with structured dropout","author":"fan","year":"2020","journal-title":"ICLRE"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2022.101429"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10269"},{"key":"ref7","article-title":"DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT","author":"chang","year":"2021","journal-title":"ICASSP"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2362"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3195430"},{"key":"ref6","article-title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","author":"chen","year":"2021","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10191"}],"event":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10192576\/10192577\/10193042.pdf?arnumber=10193042","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:42:57Z","timestamp":1692639777000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10193042\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icasspw59220.2023.10193042","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}