{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T17:45:56Z","timestamp":1742924756502,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030835262"},{"type":"electronic","value":"9783030835279"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-83527-9_30","type":"book-chapter","created":{"date-parts":[[2021,8,29]],"date-time":"2021-08-29T23:04:59Z","timestamp":1630278299000},"page":"357-370","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DNN-Based Semantic Rescoring Models for Speech Recognition"],"prefix":"10.1007","author":[{"given":"Irina","family":"Illina","sequence":"first","affiliation":[]},{"given":"Dominique","family":"Fohr","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,8,30]]},"reference":[{"key":"30_CR1","doi-asserted-by":"crossref","unstructured":"Bayer, A., Riccardi, G.: Semantic language models for automatic speech recognition. In: Proceedings of the IEEE Spoken Language Technology Workshop (SLT) (2014)","DOI":"10.1109\/SLT.2014.7078541"},{"key":"30_CR2","unstructured":"Corona, R., Thomason, J., Mooney, R.: Improving black-box speech recognition using semantic parsing. In: Proceedings of the The 8th International Joint Conference on Natural Language Processing, pp. 122\u2013127 (2017)"},{"key":"30_CR3","unstructured":"Devlin, J., Chang, M.-W., Toutanova, K.: BERT: Pre-training of deep bidirectional trans-formers for language understanding. In: NAACL-HLT (2019)"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Fernandez, H., Nguyen, H., Ghannay, S., Tomashenko, N., Est\u00e8ve, Y.: TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation. In: Proceedings of SPECOM, pp. 18\u201322 (2018)","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Fuchun P., Roy S., Shahshahani B., Beaufays F.: Search results based N-best hypothesis rescoring with maximum entropy classification. In: ASRU, pp. 422\u2013427 (2013)","DOI":"10.1109\/ASRU.2013.6707767"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Gaspers, J., Cimiano, P., Wrede, B.: Semantic parsing of speech using grammars learned with weak supervision. In: Proceedings of the HLT-NAACL, pp. 872\u2013881 (2015)","DOI":"10.3115\/v1\/N15-1088"},{"key":"30_CR7","unstructured":"Gillick, L., Cox, S.: Some statistical issues in the comparison of speech recognition algorithms. In: Proceedings of ICASSP, vol. 1, pp. 532\u2013535 (1989)"},{"key":"30_CR8","unstructured":"Huang, H., Peng, F.: An empirical study of efficient ASR rescoring with transformers. In: arXiv:1910.11450v1 (2019)"},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"Jinyu, L., Tsao, Y., Lee, C.-H.: A study on knowledge source integration for candidate rescoring in automatic speech recognition. In: ICASSP, vol. 1, pp. 837\u2013840 (2005)","DOI":"10.1109\/ICASSP.2005.1415244"},{"key":"30_CR10","unstructured":"Kumar, A., Morales, C., Vidal, M.-E., Schmidt, C., Auer, S.: Use of knowledge graph in rescoring the N-best list in automatic speech recognition. arXiv:1705.08018v1 (2017)"},{"key":"30_CR11","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1007\/978-3-030-58323-1_41","volume-title":"Text, Speech, and Dialogue","author":"S Level","year":"2020","unstructured":"Level, S., Illina, I., Fohr, D.: Introduction of semantic model to help speech recognition. In: Sojka, P., Kope\u010dek, I., Pala, K., Hor\u00e1k, A. (eds.) TSD 2020. LNCS (LNAI), vol. 12284, pp. 377\u2013385. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58323-1_41"},{"key":"30_CR12","first-page":"3111","volume":"26","author":"T Mikolov","year":"2013","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. Adv. Neural. Inf. Process. Syst. 26, 3111\u20133119 (2013)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Kombrink, S., Burget, L., Cernocky, J.-H., Khudanpur, S.: Extensions of recurrent neural network language model. In: Proceedings of the ICASSP, pp. 5528\u20135531 (2011)","DOI":"10.1109\/ICASSP.2011.5947611"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Ogawa, A., Delcroix, M., Karita, S., Nakatani, T.: Rescoring N-best speech recognition list based on one-on-one hypothesis comparaison using encoder-classifier model. In: Proceedings of the ICASSP (2018)","DOI":"10.1109\/ICASSP.2018.8461405"},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Ogawa, A., Delcroix, M., Karita, S., Nakatani, T.: Improved deep duel model for rescoring N-best speech recognition list using backward LSTMLM and ensemble encoders. In: Proceedings of Interspeech (2019)","DOI":"10.21437\/Interspeech.2019-1949"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Peddinti, V., Povey, D., Khudanpur, S.: A time delay neural network architecture for efficient modeling of long temporal contexts. In: Interspeech (2015)","DOI":"10.21437\/Interspeech.2015-647"},{"key":"30_CR17","unstructured":"Povey D., et al.: The Kaldi speech recognition toolkit. In: Proceedings of IEEE Workshop on Automatic Speech Recognition and Understanding (2011)"},{"key":"30_CR18","first-page":"1081","volume":"101","author":"J Shin","year":"2019","unstructured":"Shin, J., Lee, Y., Jung, K.: Effective sentence scoring method using BERT for speech recognition. Proc. Mach. Learn. Res. 101, 1081\u20131093 (2019)","journal-title":"Proc. Mach. Learn. Res."},{"key":"30_CR19","unstructured":"Turc, I., Chang, M.-W., Lee, K., Toutanova, K.: Well-read students learn better: on the importance of pre-training compact models. arXiv:1908.08962v2 (2019)"},{"key":"30_CR20","doi-asserted-by":"crossref","unstructured":"Varga, A., Steeneken, H.: Assessment for automatic speech recognition: II. NOISEX-92: a database and an experiment to study the effect of additive noise on speech recognition systems. Speech Commun. 12(3), 247\u2013251 (1993)","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"30_CR21","doi-asserted-by":"crossref","unstructured":"Verhasselt, J., Dercks, H.: N-best list rescoring in speech recognition. J. Acoust. Soc. Am. 128(6) (2010)","DOI":"10.1121\/1.3544449"},{"key":"30_CR22","doi-asserted-by":"crossref","unstructured":"Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., Lang, K.J.: Phoneme recognition using time-delay neural networks. IEEE Trans. Acoust. Speech Sig. Process. 37(3), 328\u2013339 (1989)","DOI":"10.1109\/29.21701"},{"key":"30_CR23","unstructured":"Wang, A., Cho, K.: BERT has a mouth, and it must speak: BERT as a Markov random field language model. In: Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation, pp. 30\u201336 (2019)"},{"key":"30_CR24","unstructured":"https:\/\/github.com\/hanxiao\/bert-as-service\/"},{"key":"30_CR25","unstructured":"https:\/\/github.com\/hanxiao\/bert-as-service#q-thecosine-similarity-of-two-sentence-vectors-is-unreasonably-high-eg-always-08-whats-wrong"}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-83527-9_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T10:58:34Z","timestamp":1725706714000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-83527-9_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030835262","9783030835279"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-83527-9_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"30 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TSD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Text, Speech, and Dialogue","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Olomouc","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.kiv.zcu.cz\/tsd2021\/","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":"TSDEngine 3.2","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"101","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":"29","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":"17","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":"29% - 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":"2,93","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)"}}]}}