{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:06:19Z","timestamp":1730297179499,"version":"3.28.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022897","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"876-883","source":"Crossref","is-referenced-by-count":0,"title":["Combining Contrastive and Non-Contrastive Losses for Fine-Tuning Pretrained Models in Speech Analysis"],"prefix":"10.1109","author":[{"given":"Florian","family":"Lux","sequence":"first","affiliation":[{"name":"University of Stuttgart, Institute for Natural Language Processing,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ching-Yi","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Stuttgart, Institute for Natural Language Processing,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ngoc Thang","family":"Vu","sequence":"additional","affiliation":[{"name":"University of Stuttgart, Institute for Natural Language Processing,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21726-5_12"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1201\/9780203166369"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1166\/asem.2018.2219"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2017.8037686"},{"issue":"2","key":"ref5","first-page":"461","article-title":"Assessment of respiratory disorders using speech parameters","volume":"4","author":"Shrivastava","year":"2018","journal-title":"International Journal on Future Revolution in Computer Science & Communication Engineering"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988261"},{"key":"ref7","article-title":"Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis","volume-title":"NeurIPS","volume":"31","author":"Jia","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1130"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-15"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref13","article-title":"DeCoAR 2.0: Deep contextualized acoustic representations with vector quantization","author":"Ling","year":"2020","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref17","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"NeurIPS","volume":"33","author":"Baevski","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1280"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref20","article-title":"Applying wav2vec2. 0 to Speech Recognition in various low-resource languages","author":"Yi","year":"2020","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001493000339"},{"key":"ref22","article-title":"Representation Learning with Contrastive Predictive Coding","author":"van den Oord","year":"2019","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"ref24","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"ICML","author":"Zbontar","year":"2021"},{"key":"ref25","first-page":"2397","article-title":"Avoiding latent variable collapse with generative skip models","volume-title":"AISTATS","author":"Dieng"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207209"},{"key":"ref27","first-page":"1","article-title":"Study of Prevention of Mode Collapse in Generative Adversarial Network (GAN)","volume-title":"CICT","author":"Kushwaha","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1975.224110"},{"key":"ref31","first-page":"128","article-title":"Least squares quantization in PCMs Bell Telephone Labs","volume":"28","author":"Lloyd","year":"1957","journal-title":"Transactions on Information Theory"},{"key":"ref32","article-title":"Prototypical networks for few-shot learning","volume-title":"NeurIPS","volume":"30","author":"Snell","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref34","first-page":"4211","article-title":"Common Voice: A Massively-Multilingual Speech Corpus","volume-title":"LREC","author":"Ardila","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.35111\/17gk-bn40"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref38","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3390\/s21144785"},{"issue":"11","key":"ref40","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022897.pdf?arnumber=10022897","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:34:51Z","timestamp":1707813291000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022897\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022897","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}