{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:32:18Z","timestamp":1772119938451,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819722648","type":"print"},{"value":"9789819722624","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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\/978-981-97-2262-4_4","type":"book-chapter","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T09:02:31Z","timestamp":1713949351000},"page":"40-52","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Accurate Semi-supervised Automatic Speech Recognition via\u00a0Multi-hypotheses-Based Curriculum Learning"],"prefix":"10.1007","author":[{"given":"Junghun","family":"Kim","sequence":"first","affiliation":[]},{"given":"Ka Hyun","family":"Park","sequence":"additional","affiliation":[]},{"given":"U","family":"Kang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,4,25]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Al-Zakarya, M.A., Al-Irhaim, Y.F.: Unsupervised and semi-supervised speech recognition system: a review. AL-Rafidain J. Comput. Sci. Math. (2023)","DOI":"10.33899\/csmj.2023.179466"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Baevski, A., Mohamed, A.: Effectiveness of self-supervised pre-training for ASR. In: ICASSP (2020)","DOI":"10.1109\/ICASSP40776.2020.9054224"},{"key":"4_CR3","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: Wav2Vec 2.0: a framework for self-supervised learning of speech representations. In: NeurIPS (2020)"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Cantiabela, Z.: Deep learning for robust speech command recognition using convolutional neural networks (CNN). In: IC3INA (2022)","DOI":"10.1145\/3575882.3575902"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, W., Wang, C.: Semi-supervised ASR by end-to-end self-training. arXiv:2001.09128 (2020)","DOI":"10.21437\/Interspeech.2020-1280"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"D\u2019Haro, L.F., Banchs, R.E.: Automatic correction of ASR outputs by using machine translation. In: INTERSPEECH (2016)","DOI":"10.21437\/Interspeech.2016-299"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Higuchi, Y., Karube, K., Ogawa, T., Kobayashi, T.: Hierarchical conditional end-to-end ASR with CTC and multi-granular subword units. In: ICASSP (2022)","DOI":"10.1109\/ICASSP43922.2022.9746580"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Javanmardi, F., Tirronen, S., Kodali, M., Kadiri, S.R., Alku, P.: Wav2Vec-based detection and severity level classification of dysarthria from speech. In: ICASSP (2023)","DOI":"10.1109\/ICASSP49357.2023.10094857"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Korkut, C., Haznedaroglu, A., Arslan, L.: Comparison of deep learning methods for spoken language identification. In: SPECOM (2020)","DOI":"10.1007\/978-3-030-60276-5_23"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Kreyssig, F.L., Shi, Y., Guo, J., Sari, L., Mohamed, A., Woodland, P.C.: Biased self-supervised learning for ASR. CoRR (2022)","DOI":"10.21437\/Interspeech.2023-2499"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Liu, M., Ke, Y., Zhang, Y., Shao, W., Song, L.: Speech emotion recognition based on deep learning. In: TENCON (2022)","DOI":"10.1109\/TENCON55691.2022.9978156"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Long, Y., Li, Y., Wei, S., Zhang, Q., Yang, C.: Large-scale semi-supervised training in deep learning acoustic model for ASR. IEEE Access (2019)","DOI":"10.1109\/ACCESS.2019.2940961"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Nguyen, Q., Valizadegan, H., Hauskrecht, M.: Learning classification models with soft-label information. J. Am. Med. Inf. Assoc. (2014)","DOI":"10.1136\/amiajnl-2013-001964"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Nguyen, T.N., Pham, N.-Q., Waibel, A.: Accent conversion using pre-trained model and synthesized data from voice conversion. In: Interspeech (2022)","DOI":"10.21437\/Interspeech.2022-10729"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Novotney, S., Schwartz, R.M., Ma, J.Z.: Unsupervised acoustic and language model training with small amounts of labelled data. In: ICASSP (2009)","DOI":"10.1109\/ICASSP.2009.4960579"},{"key":"4_CR16","unstructured":"Daniel, S., et al.: Improved noisy student training for automatic speech recognition. In: INTERSPEECH (2020)"},{"key":"4_CR17","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: ICML (2023)"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Rouhe, A., Virkkunen, A., Leinonen, J., Kurimo, M., et\u00a0al.: Low resource comparison of attention-based and hybrid ASR exploiting Wav2Vec 2.0. In: Interspeech (2022)","DOI":"10.21437\/Interspeech.2022-11318"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Schneider, S., Baevski, A., Collobert, R., Auli, M.: Wav2Vec: unsupervised pre-training for speech recognition. In: INTERSPEECH (2019)","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Shan, C., Zhang, J., Wang, Y., Xie, L.: Attention-based end-to-end speech recognition on voice search. In: ICASSP (2018)","DOI":"10.1109\/ICASSP.2018.8462492"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Vyas, A., Madikeri, S.R., Bourlard, H.: Comparing CTC and LFMMI for out-of-domain adaptation of Wav2Vec 2.0 acoustic model. In: Interspeech (2021)","DOI":"10.21437\/Interspeech.2021-1683"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Weninger, F., Mana, F., Gemello, R., Andr\u00e9s-Ferrer, J., Zhan, P.: Semi-supervised learning with data augmentation for end-to-end ASR. In: INTERSPEECH (2020)","DOI":"10.21437\/Interspeech.2020-1337"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Xu, Q., Likhomanenko, T., Kahn, J., Hannun, A.Y., Synnaeve, G., Collobert, R.: Iterative pseudo-labeling for speech recognition. In: INTERSPEECH (2020)","DOI":"10.21437\/Interspeech.2020-1800"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Zhao, X., et al.: Disentangling content and fine-grained prosody information via hybrid ASR bottleneck features for voice conversion. In: ICASSP (2022)","DOI":"10.1109\/ICASSP43922.2022.9747625"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-2262-4_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T09:16:53Z","timestamp":1713950213000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-2262-4_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819722648","9789819722624"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-2262-4_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"25 April 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taipei","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taiwan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 May 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 May 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}