{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T08:26:07Z","timestamp":1745569567807,"version":"3.28.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389731","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":6,"title":["Prompting and Adapter Tuning For Self-Supervised Encoder-Decoder Speech Model"],"prefix":"10.1109","author":[{"given":"Kai-Wei","family":"Chang","sequence":"first","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming-Hsin","family":"Chen","sequence":"additional","affiliation":[{"name":"National Taiwan University,Department of Computer Science and Information Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun-Ping","family":"Lin","sequence":"additional","affiliation":[{"name":"National Taiwan University,Department of Computer Science and Information Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing Neng","family":"Hsu","sequence":"additional","affiliation":[{"name":"National Taiwan University,Department of Computer Science and Information Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul Kuo-Ming","family":"Huang","sequence":"additional","affiliation":[{"name":"National Taiwan University,Department of Computer Science and Information Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chien-Yu","family":"Huang","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shang-Wen","family":"Li","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Representation learning with contrastive predictive coding","author":"den Oord","year":"2018","journal-title":"arXiv preprint"},{"key":"ref2","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref6","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"et al","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.593"},{"key":"ref8","article-title":"Textually pretrained speech language models","author":"et al","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096988"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref11","first-page":"2790","article-title":"Paramet-erefficient transfer learning for nlp","volume-title":"in International Conference on Machine Learning","author":"Houlsby"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10610"},{"key":"ref13","article-title":"SpeechPrompt v2: Prompt tuning for speech classification tasks","author":"Chang","year":"2023","journal-title":"arXiv preprint arXiv:2303.00733"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096311"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023274"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref17","article-title":"Pre-training transformer decoder for end-to-end asr model with unpaired speech data","author":"et al","year":"2022","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3288409"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11338"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1250"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref24","article-title":"SpeechGen: Unlocking the generative power of speech language models with prompts","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Adversarial reprogramming of neural networks","author":"Elsayed","year":"2019","journal-title":"in ICLR (Poster)"},{"key":"ref26","article-title":"Model reprogramming: Resource-efficient cross-domain machine learning","volume":"abs\/2202.10629","author":"Chen","year":"2022","journal-title":"CoRR"},{"key":"ref27","article-title":"Neural model reprogramming with similarity based mapping for low-resource spoken command classification","author":"Yen","year":"2021","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094903"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096568"},{"key":"ref30","article-title":"Learning multiple visual domains with residual adapters","volume":"30","author":"Rebuffi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"in ICLR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.199"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.103"},{"key":"ref34","article-title":"Residual adapters for few-shot text-to-speech speaker adaptation","author":"Morioka","year":"2022","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Attention is all you need","volume":"30","author":"et al","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref36","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","volume":"abs\/1804.03209","author":"Warden","year":"2018","journal-title":"CoRR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414922"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"article-title":"Towards a unified view of parameter-efficient transfer learning","volume-title":"in International Conference on Learning Representations","author":"He","key":"ref42"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2023,12,16]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389731.pdf?arnumber=10389731","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:42:42Z","timestamp":1706028162000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389731\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389731","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}