{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T15:36:14Z","timestamp":1759937774337,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819981403"},{"type":"electronic","value":"9789819981410"}],"license":[{"start":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T00:00:00Z","timestamp":1700956800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T00:00:00Z","timestamp":1700956800000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8141-0_5","type":"book-chapter","created":{"date-parts":[[2023,11,25]],"date-time":"2023-11-25T09:02:16Z","timestamp":1700902936000},"page":"62-73","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Effective Domain Adaptation for\u00a0Robust Dysarthric Speech Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3436-1253","authenticated-orcid":false,"given":"Shanhu","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0158-5330","authenticated-orcid":false,"given":"Jing","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7069-3752","authenticated-orcid":false,"given":"Shiliang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,26]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Bhat, C., Das, B., Vachhani, B., Kopparapu, S.K.: Dysarthric speech recognition using time-delay neural network based denoising autoencoder. In: Proceedings of INTERSPEECH 2018, pp. 451\u2013455, September 2018","DOI":"10.21437\/Interspeech.2018-1754"},{"key":"5_CR2","doi-asserted-by":"publisher","unstructured":"Chan, W., Jaitly, N., Le, Q.V., Vinyals, O.: Listen, attend and spell: a neural network for large vocabulary conversational speech recognition. In: Proceedings of ICASSP 2016, pp. 4960\u20134964, March 2016. https:\/\/doi.org\/10.1109\/ICASSP.2016.7472621","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Christensen, H., et al.: Combining in-domain and out-of-domain speech data for automatic recognition of disordered speech. In: Proceedings of INTERSPEECH 2013, pp. 3642\u20133645, August 2013","DOI":"10.21437\/Interspeech.2013-324"},{"issue":"5","key":"5_CR4","doi-asserted-by":"publisher","first-page":"1060","DOI":"10.1109\/TASL.2013.2244083","volume":"21","author":"L Deng","year":"2013","unstructured":"Deng, L., Li, X.: Machine learning paradigms for speech recognition: an overview. IEEE Trans. Speech Audio Process. 21(5), 1060\u20131089 (2013)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Ding, C., Sun, S., Zhao, J.: Multi-task transformer with input feature reconstruction for dysarthric speech recognition. In: Proceedings of ICASSP 2021, pp. 7318\u20137322, June 2021","DOI":"10.1109\/ICASSP39728.2021.9414614"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Gaur, N., et al.: Mixture of informed experts for multilingual speech recognition. In: Proceedings of ICASSP 2021, pp. 6234\u20136238, June 2021","DOI":"10.1109\/ICASSP39728.2021.9414379"},{"issue":"2","key":"5_CR7","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1109\/89.279278","volume":"2","author":"J Gauvain","year":"1994","unstructured":"Gauvain, J., Lee, C.: Maximum a posteriori estimation for multivariate gaussian mixture observations of markov chains. IEEE Trans. Speech Audio Process. 2(2), 291\u2013298 (1994)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Ghahremani, P., Manohar, V., Hadian, H., Povey, D., Khudanpur, S.: Investigation of transfer learning for ASR using LF-MMI trained neural networks. In: Proceedings of ASRU 2017, pp. 279\u2013286, December 2017","DOI":"10.1109\/ASRU.2017.8268947"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Karita, S., Soplin, N.E.Y., Watanabe, S., Delcroix, M., Ogawa, A., Nakatani, T.: Improving transformer-based end-to-end speech recognition with connectionist temporal classification and language model integration. In: Proceedings of INTERSPEECH 2019, pp. 1408\u20131412. ISCA, September 2019","DOI":"10.21437\/Interspeech.2019-1938"},{"key":"5_CR10","doi-asserted-by":"publisher","unstructured":"Karita, S., et al.: A comparative study on transformer vs RNN in speech applications. In: Proceedings of ASRU 2019, pp. 449\u2013456, December 2019. https:\/\/doi.org\/10.1109\/ASRU46091.2019.9003750","DOI":"10.1109\/ASRU46091.2019.9003750"},{"issue":"3","key":"5_CR11","doi-asserted-by":"publisher","first-page":"766","DOI":"10.1109\/TPAMI.2019.2945942","volume":"43","author":"WM Kouw","year":"2021","unstructured":"Kouw, W.M., Loog, M.: A review of domain adaptation without target labels. IEEE Trans. Pattern Anal. Mach. Intell. 43(3), 766\u2013785 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"5_CR12","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1006\/csla.1995.0010","volume":"9","author":"CJ Leggetter","year":"1995","unstructured":"Leggetter, C.J., Woodland, P.C.: Maximum likelihood linear regression for speaker adaptation of continuous density hidden markov models. Comput. Speech Lang. 9(2), 171\u2013185 (1995)","journal-title":"Comput. Speech Lang."},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Park, D.S., et al.: Specaugment: a simple data augmentation method for automatic speech recognition. In: Proceedings of INTERSPEECH 2019, pp. 2613\u20132617, September 2019","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"5_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1007\/978-3-030-92273-3_37","volume-title":"Neural Information Processing","author":"Y Qin","year":"2021","unstructured":"Qin, Y., Ding, J., Sun, Y., Ding, X.: A transformer-based model for\u00a0low-resource event detection. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds.) ICONIP 2021. LNCS, vol. 13111, pp. 452\u2013463. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-92273-3_37"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Ramponi, A., Plank, B.: Neural unsupervised domain adaptation in NLP - a survey. In: Proceedings of COLING 2020, pp. 6838\u20136855. International Committee on Computational Linguistics, December 2020","DOI":"10.18653\/v1\/2020.coling-main.603"},{"key":"5_CR16","unstructured":"Rousseau, A., Del\u00e9glise, P., Est\u00e8ve, Y.: Enhancing the TED-LIUM corpus with selected data for language modeling and more TED talks. In: Proceedings of LREC 2014 - Proceedings of the Ninth International Conference on Language Resources and Evaluation, pp. 3935\u20133939. European Language Resources Association (ELRA), May 2014"},{"issue":"4","key":"5_CR17","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/s10579-011-9145-0","volume":"46","author":"F Rudzicz","year":"2012","unstructured":"Rudzicz, F., Namasivayam, A.K., Wolff, T.: The TORGO database of acoustic and articulatory speech from speakers with dysarthria. Lang. Resour. Eval. 46(4), 523\u2013541 (2012)","journal-title":"Lang. Resour. Eval."},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Sehgal, S., Cunningham, S.P.: Model adaptation and adaptive training for the recognition of dysarthric speech. In: Proceedings of INTERSPEECH 2015, pp. 65\u201371. Association for Computational Linguistics, September 2015","DOI":"10.18653\/v1\/W15-5112"},{"key":"5_CR19","doi-asserted-by":"publisher","unstructured":"Soleymanpour, M., Johnson, M.T., Soleymanpour, R., Berry, J.: Synthesizing dysarthric speech using multi-speaker tts for dysarthric speech recognition. In: Proceedings of ICASSP 2022, pp. 7382\u20137386, May 2022. https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746585","DOI":"10.1109\/ICASSP43922.2022.9746585"},{"key":"5_CR20","volume-title":"Pattern Recognition and Machine Learning","author":"S Sun","year":"2020","unstructured":"Sun, S., Zhao, J.: Pattern Recognition and Machine Learning. Tsinghua University Press, China (2020)"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Sun, S., Yeh, C., Hwang, M., Ostendorf, M., Xie, L.: Domain adversarial training for accented speech recognition. In: Proceedings of ICASSP 2018, pp. 4854\u20134858, April 2018","DOI":"10.1109\/ICASSP.2018.8462663"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Vachhani, B., Bhat, C., Kopparapu, S.K.: Data augmentation using healthy speech for dysarthric speech recognition. In: Proceedings of INTERSPEECH 2018, pp. 471\u2013475, September 2018","DOI":"10.21437\/Interspeech.2018-1751"},{"issue":"8","key":"5_CR23","doi-asserted-by":"publisher","first-page":"1240","DOI":"10.1109\/JSTSP.2017.2763455","volume":"11","author":"S Watanabe","year":"2017","unstructured":"Watanabe, S., Hori, T., Kim, S., Hershey, J.R., Hayashi, T.: Hybrid CTC\/attention architecture for end-to-end speech recognition. IEEE J. Sel. Top. Sig. Process. 11(8), 1240\u20131253 (2017)","journal-title":"IEEE J. Sel. Top. Sig. Process."},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Wu, L., Zong, D., Sun, S., Zhao, J.: A sequential contrastive learning framework for robust dysarthric speech recognition. In: Proceedings of ICASSP 2021, pp. 7303\u20137307, June 2021","DOI":"10.1109\/ICASSP39728.2021.9415017"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Xiong, F., Barker, J., Christensen, H.: Phonetic analysis of dysarthric speech tempo and applications to robust personalised dysarthric speech recognition. In: Proceedings of ICASSP 2019, pp. 5836\u20135840, May 2019","DOI":"10.1109\/ICASSP.2019.8683091"},{"key":"5_CR26","doi-asserted-by":"publisher","unstructured":"Xiong, F., Barker, J., Yue, Z., Christensen, H.: Source domain data selection for improved transfer learning targeting dysarthric speech recognition. In: Proceedings of ICASSP 2020, pp. 7424\u20137428, May 2020. https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9054694","DOI":"10.1109\/ICASSP40776.2020.9054694"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8141-0_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T15:35:17Z","timestamp":1710344117000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8141-0_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,26]]},"ISBN":["9789819981403","9789819981410"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8141-0_5","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023,11,26]]},"assertion":[{"value":"26 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Changsha","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":"20 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1274","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":"650","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":"51% - 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":"4.14","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":"2.46","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}