{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T19:23:29Z","timestamp":1742930609642,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030878016"},{"type":"electronic","value":"9783030878023"}],"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\/978-3-030-87802-3_25","type":"book-chapter","created":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T23:36:52Z","timestamp":1632267412000},"page":"271-278","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Text and Synthetic Data for Domain Adaptation in End-to-End Speech Recognition"],"prefix":"10.1007","author":[{"given":"Juan","family":"Hussain","sequence":"first","affiliation":[]},{"given":"Christian","family":"Huber","sequence":"additional","affiliation":[]},{"given":"Sebastian","family":"St\u00fcker","sequence":"additional","affiliation":[]},{"given":"Alexander","family":"Waibel","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,22]]},"reference":[{"key":"25_CR1","unstructured":"Black, A.W., Lenzo, K.A.: Flite: a small fast run-time synthesis engine. In: 4th ISCA Tutorial and Research Workshop (ITRW) on Speech Synthesis (2001)"},{"key":"25_CR2","unstructured":"Chorowski, J., Bahdanau, D., Serdyuk, D., Cho, K., Bengio, Y.: Attention-based models for speech recognition. arXiv preprint arXiv:1506.07503 (2015)"},{"key":"25_CR3","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Drexler, J., Glass, J.: Combining end-to-end and adversarial training for low-resource speech recognition. In: 2018 IEEE Spoken Language Technology Workshop (SLT), pp. 361\u2013368. IEEE (2018)","DOI":"10.1109\/SLT.2018.8639541"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Gandhe, A., Rastrow, A.: Audio-attention discriminative language model for ASR rescoring. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7944\u20137948. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054335"},{"key":"25_CR6","doi-asserted-by":"publisher","unstructured":"Garofolo, J.S., Graff, D., Paul, D., David, P.: CSR-I (WSJ0) Sennheiser LDC93S6B. https:\/\/doi.org\/10.35111\/ap42-7n83","DOI":"10.35111\/ap42-7n83"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Graves, A.: Sequence transduction with recurrent neural networks. arXiv preprint arXiv:1211.3711 (2012)","DOI":"10.1007\/978-3-642-24797-2_3"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Hu, K., Sainath, T.N., Pang, R., Prabhavalkar, R.: Deliberation model based two-pass end-to-end speech recognition. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7799\u20137803. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053606"},{"key":"25_CR10","unstructured":"Huber, C., Hussain, J., Nguyen, T.N., Song, K., St\u00fcker, S., Waibel, A.: Supervised adaptation of sequence-to-sequence speech recognition systems using batch-weighting. In: Proceedings of the 2nd Workshop on Life-long Learning for Spoken Language Systems, pp. 9\u201317 (2020)"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Karita, S., Watanabe, S., Iwata, T., Ogawa, A., Delcroix, M.: Semi-supervised end-to-end speech recognition. In: Interspeech, pp. 2\u20136 (2018)","DOI":"10.21437\/Interspeech.2018-1746"},{"key":"25_CR12","doi-asserted-by":"publisher","unstructured":"Linguistic Data Consortium: ACL\/DCI LDC93T1. https:\/\/doi.org\/10.35111\/vdfv-av77","DOI":"10.35111\/vdfv-av77"},{"key":"25_CR13","doi-asserted-by":"publisher","unstructured":"Linguistic Data Consortium, NIST Multimodal Information Group: CSR-II (WSJ1) Sennheiser LDC94S13B. https:\/\/doi.org\/10.35111\/5jkw-xt28","DOI":"10.35111\/5jkw-xt28"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Nguyen, T.S., Stueker, S., Niehues, J., Waibel, A.: Improving sequence-to-sequence speech recognition training with on-the-fly data augmentation. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7689\u20137693. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054130"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1520\u20131528 (2015)","DOI":"10.1109\/ICCV.2015.178"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Raju, A., Filimonov, D., Tiwari, G., Lan, G., Rastrow, A.: Scalable multi corpora neural language models for ASR. arXiv preprint arXiv:1907.01677 (2019)","DOI":"10.21437\/Interspeech.2019-3060"},{"key":"25_CR17","unstructured":"Rousseau, A., Del\u00e9glise, P., Esteve, Y.: TED-LIUM: an automatic speech recognition dedicated corpus. In: LREC, pp. 125\u2013129 (2012)"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Sainath, T.N., et al.: Two-pass end-to-end speech recognition. arXiv preprint arXiv:1908.10992 (2019)","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"25_CR19","unstructured":"Sanabria, R., et al.: How2: a large-scale dataset for multimodal language understanding. arXiv preprint arXiv:1811.00347 (2018)"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909 (2015)","DOI":"10.18653\/v1\/P16-1162"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Zheng, X., Liu, Y., Gunceler, D., Willett, D.: Using synthetic audio to improve the recognition of out-of-vocabulary words in end-to-end ASR systems. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5674\u20135678. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9414778"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87802-3_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T23:45:32Z","timestamp":1632267932000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87802-3_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030878016","9783030878023"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87802-3_25","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":"22 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"St Petersburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","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":"27 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2021\/","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":"163","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":"74","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":"45% - 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":"3.5","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":"5.5","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)"}},{"value":"The conference was held online due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}