{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T09:10:06Z","timestamp":1743066606784,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819794362"},{"type":"electronic","value":"9789819794379"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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":[[2025]]},"DOI":"10.1007\/978-981-97-9437-9_32","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:28:26Z","timestamp":1730392106000},"page":"407-419","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ASRLM: ASR-Robust Language Model Pre-training via\u00a0Generative and\u00a0Discriminative Learning"],"prefix":"10.1007","author":[{"given":"Qian","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiting","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yitong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junlan","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"32_CR1","doi-asserted-by":"crossref","unstructured":"Peng, Y., Arora, S., Higuchi, Y., et al.: A study on the integration of pre-trained ssl, asr, lm and slu models for spoken language understanding. In: 2022 IEEE Spoken Language Technology Workshop (SLT), pp. 406\u2013413. IEEE (2023)","DOI":"10.1109\/SLT54892.2023.10022399"},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Futami, H., Huynh, J., Arora, S., et al.: The Pipeline System of ASR and NLU with MLM-based data Augmentation Toward Stop Low-Resource Challenge. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20132. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10096049"},{"key":"32_CR3","doi-asserted-by":"crossref","unstructured":"Shao, Y., Kumar, A., Nakashole, N.: Database-aware ASR error correction for speech-to-SQL parsing. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10097246"},{"key":"32_CR4","doi-asserted-by":"crossref","unstructured":"Shivakumar, P.G., Yang, M., Georgiou, P.: Spoken language intent detection using confusion2vec. arxiv preprint arxiv:1904.03576 (2019)","DOI":"10.21437\/Interspeech.2019-2226"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Weng, Z., Qin, Z., Tao, X., et al.: Deep learning enabled semantic communications with speech recognition and synthesis. IEEE Trans. Wirel. Commun. (2023)","DOI":"10.1109\/TWC.2023.3240969"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Tsunoo, E., Kashiwagi, Y., Narisetty, C., et al.: Residual language model for end-to-end speech recognition. arxiv preprint arxiv:2206.07430 (2022)","DOI":"10.21437\/Interspeech.2022-10557"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Omelianchuk, K., Atrasevych, V., Chernodub, A., et al.: GECToR\u2013grammatical error correction: tag, not rewrite. arxiv preprint arxiv:2005.12592 (2020)","DOI":"10.18653\/v1\/2020.bea-1.16"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Su, D., Fung, P.: Improving spoken question answering using contextualized word representation. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8004\u20138008. IEEE 2020)","DOI":"10.1109\/ICASSP40776.2020.9053979"},{"key":"32_CR9","unstructured":"Clark, K., Luong, M.T., Le, Q.V., et al.: Electra: pre-training text encoders as discriminators rather than generators. arxiv preprint arxiv:2003.10555 (2020)"},{"key":"32_CR10","unstructured":"He, B., Jiang, X., ao J., et al.: Kgplm: knowledge-guided language model pre-training via generative and discriminative learning. arxiv preprint arxiv:2012.03551 (2020)"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Chi, Z., Huang, S., Dong, L., et al.: Xlm-e: cross-lingual language model pre-training via electra. arxiv preprint arxiv:2106.16138 (2021)","DOI":"10.18653\/v1\/2022.acl-long.427"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Henderson, M., Thomson, B., Young, S.: Word-based dialog state tracking with recurrent neural networks. In: Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pp. 292\u2013299 (2014)","DOI":"10.3115\/v1\/W14-4340"},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Hemphill, C.T., Godfrey, J.J., Doddington, G.R.: The ATIS spoken language systems pilot corpus. In: Speech and Natural Language: Proceedings of a Workshop Held at Hidden Valley, Pennsylvania, June 24-27, 1990 (1990)","DOI":"10.3115\/116580.116613"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., et al.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018)","DOI":"10.18653\/v1\/W18-5446"},{"key":"32_CR15","unstructured":"Xu, L., Hu, H., Zhang, X., et al.: CLUE: A Chinese language understanding evaluation benchmark. arXiv preprint arXiv:2004.05986 (2020)"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Hrinchuk, O., Popova, M., Ginsburg, B.: Correction of automatic speech recognition with transformer sequence-to-sequence model. In: Icassp 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (icassp), pp. 7074\u20137078. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053051"},{"key":"32_CR17","doi-asserted-by":"crossref","unstructured":"Liu, S., Yang, T., Yue, T., et al.: PLOME: pre-training with misspelled knowledge for Chinese spelling correction. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 2991\u20133000 (2021)","DOI":"10.18653\/v1\/2021.acl-long.233"},{"key":"32_CR18","doi-asserted-by":"crossref","unstructured":"Dighe, P., Su, Y., Zheng, S., et al.: Leveraging large language models for exploiting asr uncertainty. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp. 12231\u201312235 (2024)","DOI":"10.1109\/ICASSP48485.2024.10446132"},{"key":"32_CR19","unstructured":"Chen, C., Hu, Y., Yang, C.H.H., et al.: Hyporadise: an open baseline for generative speech recognition with large language models. Advances in Neural Information Processing Systems (2024). 36"},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Wang, L., Fazel-Zarandi, M., Tiwari, A., et al.: Data augmentation for training dialog models robust to speech recognition errors. arXiv preprint arXiv:2006.05635 (2020)","DOI":"10.18653\/v1\/2020.nlp4convai-1.8"},{"key":"32_CR21","unstructured":"Fazel-Zarandi, M., Wang, L., Tiwari, A., et al.: Investigation of error simulation techniques for learning dialog policies for conversational error recovery. arXiv preprint arXiv:1911.03378 (2019)"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Paturi, R., Srinivasan, S., Li, X.: Lexical speaker error correction: Leveraging language models for speaker diarization error correction. arxiv preprint arxiv:2306.09313 (2023)","DOI":"10.21437\/Interspeech.2023-1982"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Feng, L., Yu, J., Cai, D., et al.: ASR-Robust Spoken Language Understanding on ASR-GLUE dataset (2022)","DOI":"10.21437\/Interspeech.2022-10097"},{"key":"32_CR24","doi-asserted-by":"publisher","first-page":"40","DOI":"10.3758\/BF03213026","volume":"9","author":"JT Townsend","year":"1971","unstructured":"Townsend, J.T.: Theoretical analysis of an alphabetic confusion matrix. Perception Psychophys. 9, 40\u201350 (1971)","journal-title":"Perception Psychophys."},{"key":"32_CR25","unstructured":"Wang, S., Gunter, T., VanDyke, D.: On modelling uncertainty in neural language generation for policy optimisation in voice-triggered dialog assistants. In: 2nd Workshop on Conversational AI: Today\u2019s Practice and Tomorrow\u2019s Potential, NeurIPS (2018)"},{"key":"32_CR26","unstructured":"Devlin, J., Chang, M.W., Lee, K., et al.: Bert: pre-training of deep bidirectional transformers for language understanding. arxiv preprint arxiv:1810.04805 (2018)"},{"key":"32_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, S., Huang, H., Liu, J., et al.: Spelling error correction with soft-masked BERT. arxiv preprint arxiv:2005.07421 (2020)","DOI":"10.18653\/v1\/2020.acl-main.82"},{"key":"32_CR28","unstructured":"Dyer, C., Chahuneau, V., Smith, N.A.: A simple, fast, and effective reparameterization of IBM model 2. In: Proceedings of the 2013 Conference of the North American chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 644\u2013648 (2013)"},{"key":"32_CR29","unstructured":"Li, C.H., Wu, S.L., Liu, C.L., et al.: Spoken SQuAD: a study of mitigating the impact of speech recognition errors on listening comprehension. arxiv preprint arxiv:1804.00320 (2018)"},{"key":"32_CR30","unstructured":"Coucke, A., Saade, A., Ball, A., et al.: Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces. arxiv preprint arxiv:1805.10190 (2018)"},{"key":"32_CR31","doi-asserted-by":"crossref","unstructured":"Lee, C.H., Wang, S.M., Chang, H.C., et al.: ODSQA: open-domain spoken question answering dataset. In: 2018 IEEE Spoken Language Technology Workshop (SLT), pp. 949\u2013956. IEEE (2018)","DOI":"10.1109\/SLT.2018.8639505"},{"key":"32_CR32","doi-asserted-by":"crossref","unstructured":"Henderson, M., Thomson, B., Williams, J.D.: The second dialog state tracking challenge. In: Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pp. 263\u2013272 (2014)","DOI":"10.3115\/v1\/W14-4337"},{"key":"32_CR33","unstructured":"Achiam, J., Adler, S., Agarwal, S., et al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"}],"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\/978-981-97-9437-9_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:33:18Z","timestamp":1730392398000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-9437-9_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819794362","9789819794379"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-9437-9_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","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":"Hangzhou","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2024\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}