{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T00:28:06Z","timestamp":1726100886189},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1016\/j.neucom.2024.128493","type":"journal-article","created":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T02:04:25Z","timestamp":1724897065000},"page":"128493","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Meta-Adaptable-Adapter: Efficient adaptation of self-supervised models for low-resource speech recognition"],"prefix":"10.1016","volume":"609","author":[{"given":"Yaqi","family":"Chen","sequence":"first","affiliation":[]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xukui","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Wenlin","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Dan","family":"Qu","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2024.128493_b1","series-title":"International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume":"202","author":"Radford","year":"2023"},{"year":"2023","series-title":"Google USM: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","key":"10.1016\/j.neucom.2024.128493_b2"},{"year":"2009","series-title":"Ethnologue : Languages of the world","author":"Lewis","key":"10.1016\/j.neucom.2024.128493_b3"},{"key":"10.1016\/j.neucom.2024.128493_b4","series-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA","first-page":"506","article-title":"Learning multiple visual domains with residual adapters","author":"Rebuffi","year":"2017"},{"article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","year":"2020","series-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, Virtual","author":"Baevski","key":"10.1016\/j.neucom.2024.128493_b5"},{"key":"10.1016\/j.neucom.2024.128493_b6","doi-asserted-by":"crossref","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","article-title":"HuBERT: Self-supervised speech representation learning by masked prediction of hidden units","volume":"29","author":"Hsu","year":"2021","journal-title":"IEEE ACM Trans. Audio Speech Lang. Process."},{"year":"2023","series-title":"Scaling speech technology to 1, 000+ languages","author":"Pratap","key":"10.1016\/j.neucom.2024.128493_b7"},{"key":"10.1016\/j.neucom.2024.128493_b8","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021","first-page":"2208","article-title":"On the effectiveness of adapter-based tuning for pretrained language model adaptation","author":"He","year":"2021"},{"key":"10.1016\/j.neucom.2024.128493_b9","series-title":"Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA","first-page":"2790","volume":"97","author":"Houlsby","year":"2019"},{"year":"2021","series-title":"What all do audio transformer models hear? Probing acoustic representations for language delivery and its structure","author":"Shah","key":"10.1016\/j.neucom.2024.128493_b10"},{"year":"2022","series-title":"Parameter efficient transfer learning for various speech processing tasks","author":"Otake","key":"10.1016\/j.neucom.2024.128493_b11"},{"article-title":"Simple, scalable adaptation for neural machine translation","year":"2019","series-title":"Conference on Empirical Methods in Natural Language Processing","author":"Bapna","key":"10.1016\/j.neucom.2024.128493_b12"},{"key":"10.1016\/j.neucom.2024.128493_b13","series-title":"International Conference on Automated Machine Learning, AutoML 2022, 25-27 July 2022, Johns Hopkins University, Baltimore, MD, USA","first-page":"19\/1","article-title":"Meta-adapters: Parameter efficient few-shot fine-tuning through meta-learning","volume":"188","author":"Bansal","year":"2022"},{"key":"10.1016\/j.neucom.2024.128493_b14","series-title":"Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5-10, 2016, Barcelona, Spain","first-page":"3630","article-title":"Matching networks for one shot learning","author":"Vinyals","year":"2016"},{"key":"10.1016\/j.neucom.2024.128493_b15","series-title":"2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC)","first-page":"178","article-title":"Prototypical siamese networks for few-shot learning","author":"Wang","year":"2020"},{"article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","year":"2017","series-title":"International Conference on Machine Learning","author":"Finn","key":"10.1016\/j.neucom.2024.128493_b16"},{"article-title":"Rapid learning or feature reuse? Towards understanding the effectiveness of MAML","year":"2020","series-title":"8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020","author":"Raghu","key":"10.1016\/j.neucom.2024.128493_b17"},{"key":"10.1016\/j.neucom.2024.128493_b18","doi-asserted-by":"crossref","first-page":"3458","DOI":"10.1109\/TNNLS.2020.3011526","article-title":"Learning to learn adaptive classifier\u2013predictor for few-shot learning","volume":"32","author":"Lai","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2024.128493_b19","first-page":"2554","article-title":"Meta networks","volume":"70","author":"Munkhdalai","year":"2017","journal-title":"Proc. Mach. Learn. Res"},{"article-title":"Improving generalization in meta-learning via task augmentation","year":"2020","series-title":"International Conference on Machine Learning","author":"Yao","key":"10.1016\/j.neucom.2024.128493_b20"},{"key":"10.1016\/j.neucom.2024.128493_b21","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16-20, 2020","first-page":"7654","article-title":"MAD-X: An adapter-based framework for multi-task cross-lingual transfer","author":"Pfeiffer","year":"2020"},{"article-title":"Adapt-and-adjust: Overcoming the long-tail problem of multilingual speech recognition","year":"2020","series-title":"Interspeech","author":"Winata","key":"10.1016\/j.neucom.2024.128493_b22"},{"article-title":"Adaptable adapters","year":"2022","series-title":"North American Chapter of the Association for Computational Linguistics","author":"Moosavi","key":"10.1016\/j.neucom.2024.128493_b23"},{"key":"10.1016\/j.neucom.2024.128493_b24","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP 2021, (Volume 2: Short Papers), Virtual Event, August 1-6, 2021","first-page":"817","article-title":"Lightweight adapter tuning for multilingual speech translation","author":"Le","year":"2021"},{"key":"10.1016\/j.neucom.2024.128493_b25","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, on, Canada, June 6-11, 2021","first-page":"7028","article-title":"Meta-adapter: Efficient cross-lingual adaptation with meta-learning","author":"Hou","year":"2021"},{"key":"10.1016\/j.neucom.2024.128493_b26","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022","first-page":"7102","article-title":"Efficient adapter transfer of self-supervised speech models for automatic speech recognition","author":"Thomas","year":"2022"},{"key":"10.1016\/j.neucom.2024.128493_b27","first-page":"5149","article-title":"Meta-learning in neural networks: A survey","volume":"44","author":"Hospedales","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2024.128493_b28","series-title":"Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020","first-page":"1276","article-title":"Learning fast adaptation on cross-accented speech recognition","author":"Winata","year":"2020"},{"key":"10.1016\/j.neucom.2024.128493_b29","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, on, Canada, June 6-11, 2021","first-page":"6259","article-title":"Meta-learning for low-resource speech emotion recognition","author":"Chopra","year":"2021"},{"key":"10.1016\/j.neucom.2024.128493_b30","series-title":"IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019, Singapore, December 14-18, 2019","first-page":"881","article-title":"Speaker adaptive training using model agnostic meta-learning","author":"Klejch","year":"2019"},{"first-page":"14112","article-title":"Adversarial meta sampling for multilingual low-resource speech recognition","year":"2021","author":"Xiao","key":"10.1016\/j.neucom.2024.128493_b31"},{"key":"10.1016\/j.neucom.2024.128493_b32","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022","first-page":"4798","article-title":"Improved meta learning for low resource speech recognition","author":"Singh","year":"2022"},{"article-title":"Meta learning with adaptive loss weight for low-resource speech recognition","year":"2023","series-title":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Wang","key":"10.1016\/j.neucom.2024.128493_b33"},{"year":"2022","series-title":"M4adapter: Multilingual multi-domain adaptation for machine translation with a meta-adapter","author":"Lai","key":"10.1016\/j.neucom.2024.128493_b34"},{"key":"10.1016\/j.neucom.2024.128493_b35","doi-asserted-by":"crossref","first-page":"1227","DOI":"10.1109\/JSTSP.2022.3184480","article-title":"Improving automatic speech recognition performance for low-resource languages with self-supervised models","volume":"16","author":"Zhao","year":"2022","journal-title":"IEEE J. Sel. Top. Sign. Proces."},{"key":"10.1016\/j.neucom.2024.128493_b36","series-title":"Proceedings of the 12th Language Resources and Evaluation Conference, LREC 2020, Marseille, France, May 11-16, 2020","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2020"},{"key":"10.1016\/j.neucom.2024.128493_b37","series-title":"IEEE Spoken Language Technology Workshop, SLT 2022, Doha, Qatar, January 9-12, 2023","first-page":"798","article-title":"FLEURS: FEW-shot learning evaluation of universal representations of speech","author":"Conneau","year":"2022"},{"key":"10.1016\/j.neucom.2024.128493_b38","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1109\/TASLP.2021.3138674","article-title":"Exploiting adapters for cross-lingual low-resource speech recognition","volume":"30","author":"Hou","year":"2022","journal-title":"IEEE ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.neucom.2024.128493_b39","series-title":"Proceedings of the 12th Language Resources and Evaluation Conference","isbn-type":"print","first-page":"6494","article-title":"Open-source Multi-speaker Speech Corpora for Building Gujarati, Kannada, Malayalam, Marathi, Tamil and Telugu Speech Synthesis Systems","author":"He","year":"2020","ISBN":"http:\/\/id.crossref.org\/isbn\/9791095546344"},{"key":"10.1016\/j.neucom.2024.128493_b40","series-title":"Proceedings of the 12th Language Resources and Evaluation Conference","isbn-type":"print","first-page":"6328","article-title":"Burmese Speech Corpus, Finite-State Text Normalization and Pronunciation Grammars with an Application to Text-to-Speech","author":"Oo","year":"2020","ISBN":"http:\/\/id.crossref.org\/isbn\/9791095546344"},{"key":"10.1016\/j.neucom.2024.128493_b41","series-title":"Proceedings of Interspeech 2020","first-page":"404","article-title":"Developing an open-source Corpus of Yoruba Speech","author":"Gutkin","year":"2020"},{"issue":"6","key":"10.1016\/j.neucom.2024.128493_b42","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","article-title":"WavLM: Large-scale self-supervised pre-training for full stack speech processing","volume":"16","author":"Chen","year":"2022","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"10.1016\/j.neucom.2024.128493_b43","series-title":"Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020","first-page":"1037","article-title":"Large-scale end-to-end multilingual speech recognition and language identification with multi-task learning","author":"Hou","year":"2020"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231224012645?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231224012645?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T12:11:19Z","timestamp":1726056679000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231224012645"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":43,"alternative-id":["S0925231224012645"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2024.128493","relation":{},"ISSN":["0925-2312"],"issn-type":[{"type":"print","value":"0925-2312"}],"subject":[],"published":{"date-parts":[[2024,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Meta-Adaptable-Adapter: Efficient adaptation of self-supervised models for low-resource speech recognition","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2024.128493","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"128493"}}
