{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T01:29:26Z","timestamp":1743038966965,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031446924"},{"type":"electronic","value":"9783031446931"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-44693-1_28","type":"book-chapter","created":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T08:02:39Z","timestamp":1696665759000},"page":"349-360","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Task-Consistent Meta Learning for\u00a0Low-Resource Speech Recognition"],"prefix":"10.1007","author":[{"given":"Yaqi","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xukui","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenlin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Qu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,8]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Luo, J., Wang, J., Cheng, N., Zheng, Z., Xiao, J.: Adaptive activation network for low resource multilingual speech recognition. In: IJCNN, pp. 1\u20137 (2022)","DOI":"10.1109\/IJCNN55064.2022.9892396"},{"key":"28_CR2","first-page":"5149","volume":"44","author":"TM Hospedales","year":"2020","unstructured":"Hospedales, T.M., Antoniou, A., Micaelli, P., Storkey, A.J.: Meta-learning in neural networks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 44, 5149\u20135169 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Hsu, J.-Y., Chen, Y.-J., Lee, H.-Y.: Meta learning for end-to-end low-resource speech recognition. In: ICASSP 2020, pp. 7844\u20137848. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053112"},{"key":"28_CR4","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: Precup, D., Teh, Y.W. (eds.) ICML, vol. 70, pp. 1126\u20131135 (2017)"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Klejch, O., Fainberg, J., Bell, P., Renals, S.: Speaker adaptive training using model agnostic meta-learning. In: ASRU, pp. 881\u2013888 (2019)","DOI":"10.1109\/ASRU46091.2019.9003751"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Winata, G.I., Cahyawijaya, S., Liu, Z., Lin, Z., Madotto, A., Xu, P., Fung, P.: Learning fast adaptation on cross-accented speech recognition. In: Meng, H., Xu, B., Zheng, T.F. (eds.) Interspeech, pp. 1276\u20131280 (2020)","DOI":"10.21437\/Interspeech.2020-45"},{"key":"28_CR7","unstructured":"Naman, A., Deepshikha, K.: Indic languages automatic speech recognition using meta-learning approach. In: InterSpeech (2021)"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Chopra, S., Mathur, P., Sawhney, R., Shah, R.R.: Meta-learning for low-resource speech emotion recognition. In: ICASSP, pp. 6259\u20136263 (2021)","DOI":"10.1109\/ICASSP39728.2021.9414373"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Gong, K., Zhou, P., Zheng, G., Liang, X., Lin, L.: Adversarial meta sampling for multilingual low-resource speech recognition. In: AAAI (2020)","DOI":"10.1609\/aaai.v35i16.17661"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Hou, W., Wang, Y., Gao, S., Shinozaki, T.: Meta-adapter: efficient cross-lingual adaptation with meta-learning. In: ICASSP, pp. 7028\u20137032 (2021)","DOI":"10.1109\/ICASSP39728.2021.9414959"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Singh, S., Wang, R., Hou, F.: Improved meta learning for low resource speech recognition. In: ICASSP, pp. 4798\u20134802 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746899"},{"key":"28_CR12","unstructured":"Baevski, A., Zhou, H., Mohamed, A.R., Auli, M.: Wav2vec 2.0: a framework for self-supervised learning of speech representations. ArXiv, abs\/2006.11477 (2020)"},{"key":"28_CR13","doi-asserted-by":"publisher","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","volume":"29","author":"W-N Hsu","year":"2021","unstructured":"Hsu, W.-N., Bolte, B., Tsai, Y.-H.H., Lakhotia, K., Salakhutdinov, R., Mohamed, A.R.: HuBERT: self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 3451\u20133460 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"28_CR14","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","volume":"16","author":"S Chen","year":"2021","unstructured":"Chen, S., et al.: WavLM: large-scale self-supervised pre-training for full stack speech processing. IEEE J. Sel. Top. Signal Process. 16, 1505\u20131518 (2021)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"28_CR15","unstructured":"Eshratifar, A.E., Eigen, D., Pedram, M.: Gradient agreement as an optimization objective for meta-learning. CoRR, abs\/1810.08178 (2018)"},{"key":"28_CR16","unstructured":"Du, Y., Czarnecki, W.M., Jayakumar, S.M., Pascanu, R., Lakshminarayanan, B.: Adapting auxiliary losses using gradient similarity. ArXiv, abs\/1812.02224 (2018)"},{"key":"28_CR17","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., Finn, C.: Gradient surgery for multi-task learning. In: Larochelle, H., Ranzato, M.A., Hadsell, R., Balcan, M.-F., Lin, H.-T. (eds.) NeurIPS 2020 (2020)"},{"key":"28_CR18","unstructured":"Guiroy, S., Verma, V., Pal, C.: Towards understanding generalization in gradient-based meta-learning. ArXiv, abs\/1907.07287 (2019)"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Kim, S., Hori, T., Watanabe, S.: Joint CTC-attention based end-to-end speech recognition using multi-task learning. In: ICASSP, pp. 4835\u20134839 (2016)","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"28_CR20","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1109\/TASLP.2021.3138674","volume":"30","author":"W Hou","year":"2021","unstructured":"Hou, W., Zhu, H., Wang, Y., Wang, J., Qin, T., Renjun, X., Shinozaki, T.: Exploiting adapters for cross-lingual low-resource speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 30, 317\u2013329 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: ACL. The Association for Computer Linguistics (2016)","DOI":"10.18653\/v1\/P16-1162"},{"key":"28_CR22","unstructured":"Zhou, S., Xu, S., Xu, B.: Multilingual end-to-end speech recognition with a single transformer on low-resource languages. ArXiv, abs\/1806.05059 (2018)"},{"key":"28_CR23","unstructured":"Raghu, A., Raghu, M., Bengio, S., Vinyals, O.: Rapid learning or feature reuse? Towards understanding the effectiveness of MAML. In: ICLR (2020)"},{"key":"28_CR24","unstructured":"Gales, M.J.F., Knill, K.M., Ragni, A., Rath, S.P.: Speech recognition and keyword spotting for low-resource languages: babel project research at CUED. In: SLTU, pp. 16\u201323. ISCA (2014)"},{"key":"28_CR25","unstructured":"Povey, D., et al.: The kaldi speech recognition toolkit (2011)"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Park, D.S., et al.: SpecAugment: a simple data augmentation method for automatic speech recognition. In: Interspeech (2019)","DOI":"10.21437\/Interspeech.2019-2680"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44693-1_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T08:21:31Z","timestamp":1696839691000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44693-1_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031446924","9783031446931"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44693-1_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"8 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Foshan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2023\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Softconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"478","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"143","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"30% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}