{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:17Z","timestamp":1775229917861,"version":"3.50.1"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031404979","type":"print"},{"value":"9783031404986","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-40498-6_28","type":"book-chapter","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T23:02:34Z","timestamp":1692745354000},"page":"317-327","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Multilingual TTS Accent Impressions for\u00a0Accented ASR"],"prefix":"10.1007","author":[{"given":"Georgios","family":"Karakasidis","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nathaniel","family":"Robinson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaroslav","family":"Getman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atieno","family":"Ogayo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ragheb","family":"Al-Ghezi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ananya","family":"Ayasi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David R.","family":"Mortensen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mikko","family":"Kurimo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,23]]},"reference":[{"key":"28_CR1","unstructured":"Ardila, R., et al.: Common voice: a massively-multilingual speech corpus. arXiv preprint arXiv:1912.06670 (2019)"},{"key":"28_CR2","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. In: Advances in Neural Information Processing Systems, vol. 33, 12449\u201312460 (2020)"},{"issue":"1","key":"28_CR3","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1146\/annurev.anthro.30.1.527","volume":"30","author":"RM Bhatt","year":"2001","unstructured":"Bhatt, R.M.: World Englishes. Ann. Rev. Anthropol. 30(1), 527\u2013550 (2001)","journal-title":"Ann. Rev. Anthropol."},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Cumbal, R., Moell, B., \u00c1guas Lopes, J.D., Engwall, O.: \u201cYou don\u2019t understand me!\u201d: Comparing ASR results for L1 and L2 speakers of Swedish. In: Interspeech 2021 (2021)","DOI":"10.21437\/Interspeech.2021-2140"},{"key":"28_CR5","doi-asserted-by":"publisher","unstructured":"Das, N., Bodapati, S., Sunkara, M., Srinivasan, S., Chau, D.H.: Best of both worlds: robust accented speech recognition with adversarial transfer learning. In: Interspeech 2021, pp. 1314\u20131318. ISCA (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-1888. https:\/\/www.isca-speech.org\/archive\/interspeech_2021\/das21b_interspeech.html","DOI":"10.21437\/Interspeech.2021-1888"},{"key":"28_CR6","doi-asserted-by":"publisher","unstructured":"Du, C., Yu, K.: Speaker augmentation for low resource speech recognition. In: 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020, pp. 7719\u20137723 (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053139","DOI":"10.1109\/ICASSP40776.2020.9053139"},{"issue":"1","key":"28_CR7","doi-asserted-by":"publisher","first-page":"126","DOI":"10.3390\/e22010126","volume":"22","author":"M Gerlach","year":"2020","unstructured":"Gerlach, M., Font-Clos, F.: A standardized project Gutenberg corpus for statistical analysis of natural language and quantitative linguistics. Entropy 22(1), 126 (2020)","journal-title":"Entropy"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Graddol, D.: The decline of the native speaker. Translation Today: Trends and Perspectives, pp. 152\u2013167 (2003)","DOI":"10.21832\/9781853596179-013"},{"key":"28_CR9","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1007\/978-3-030-87802-3_29","volume-title":"Speech and Computer","author":"V Kadyan","year":"2021","unstructured":"Kadyan, V., Kathania, H., Govil, P., Kurimo, M.: Synthesis speech based data augmentation for low resource children\u00a0ASR. In: Karpov, A., Potapova, R. (eds.) SPECOM 2021. LNCS (LNAI), vol. 12997, pp. 317\u2013326. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87802-3_29"},{"key":"28_CR10","doi-asserted-by":"publisher","unstructured":"Kulkarni, K., Sengupta, S., Ramasubramanian, V., Bauer, J.G., Stemmer, G.: Accented Indian English ASR: some early results. In: 2008 IEEE Spoken Language Technology Workshop, pp. 225\u2013228 (2008). https:\/\/doi.org\/10.1109\/SLT.2008.4777881","DOI":"10.1109\/SLT.2008.4777881"},{"issue":"3","key":"28_CR11","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1093\/elt\/ccl001","volume":"60","author":"IC Kuo","year":"2006","unstructured":"Kuo, I.C.: Addressing the issue of teaching English as a lingua franca. ELT J. 60(3), 213\u2013221 (2006)","journal-title":"ELT J."},{"key":"28_CR12","doi-asserted-by":"publisher","unstructured":"Laptev, A., Korostik, R., Svischev, A., Andrusenko, A., Medennikov, I., Rybin, S.: You do not need more data: improving end-to-end speech recognition by text-to-speech data augmentation. In: 2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), pp. 439\u2013444 (2020). https:\/\/doi.org\/10.1109\/CISP-BMEI51763.2020.9263564","DOI":"10.1109\/CISP-BMEI51763.2020.9263564"},{"key":"28_CR13","doi-asserted-by":"publisher","unstructured":"Li, S., Ouyang, B., Liao, D., Xia, S., Li, L., Hong, Q.: End-to-end multi-accent speech recognition with unsupervised accent modelling. In: 2021 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, pp. 6418\u20136422 (2021). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9414833. iSSN 2379-190X","DOI":"10.1109\/ICASSP39728.2021.9414833"},{"key":"28_CR14","doi-asserted-by":"publisher","unstructured":"Lo, C.C., et al.: MOSNet: deep learning-based objective assessment for voice conversion. In: Proceedings of the Interspeech 2019, pp. 1541\u20131545 (2019). https:\/\/doi.org\/10.21437\/Interspeech.2019-2003","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"28_CR15","unstructured":"Markl, N., McNulty, S.J.: Language technology practitioners as language managers: arbitrating data bias and predictive bias in ASR. In: Proceedings of the Thirteenth Language Resources and Evaluation Conference, pp. 6328\u20136339 (2022)"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Martin, J.L.: Spoken corpora data, automatic speech recognition, and bias against African American language: the case of Habitual\u2019Be\u2019. In: Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, pp. 284\u2013284 (2021)","DOI":"10.1145\/3442188.3445893"},{"key":"28_CR17","doi-asserted-by":"publisher","unstructured":"Mimura, M., Ueno, S., Inaguma, H., Sakai, S., Kawahara, T.: Leveraging sequence-to-sequence speech synthesis for enhancing acoustic-to-word speech recognition. In: 2018 IEEE Spoken Language Technology Workshop (SLT), pp. 477\u2013484 (2018). https:\/\/doi.org\/10.1109\/SLT.2018.8639589","DOI":"10.1109\/SLT.2018.8639589"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: Librispeech: an ASR corpus based on public domain audio books. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5206\u20135210. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"28_CR19","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. arXiv preprint arXiv:2212.04356 (2022)"},{"key":"28_CR20","doi-asserted-by":"publisher","unstructured":"Robinson, N.R., Ogayo, P., Gangu, S.R., Mortensen, D.R., Watanabe, S.: When is TTS augmentation through a pivot language useful? In: Proceedings of the Interspeech 2022, pp. 3538\u20133542 (2022). https:\/\/doi.org\/10.21437\/Interspeech.2022-11203","DOI":"10.21437\/Interspeech.2022-11203"},{"key":"28_CR21","doi-asserted-by":"publisher","unstructured":"Rossenbach, N., Zeyer, A., Schl\u00fcter, R., Ney, H.: Generating synthetic audio data for attention-based speech recognition systems. In: 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020, pp. 7069\u20137073 (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053008. iSSN 2379-190X","DOI":"10.1109\/ICASSP40776.2020.9053008"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Shi, X., et al.: The accented English speech recognition challenge 2020: open datasets, tracks, baselines, results and methods. CoRR arXiv:2102.10233 (2021)","DOI":"10.1109\/ICASSP39728.2021.9413386"},{"key":"28_CR23","doi-asserted-by":"publisher","unstructured":"Tan, T., Lu, Y., Ma, R., Zhu, S., Guo, J., Qian, Y.: AISpeech-SJTU ASR system for the accented English speech recognition challenge. In: 2021 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, pp. 6413\u20136417 (2021). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9414471. iSSN 2379-190X","DOI":"10.1109\/ICASSP39728.2021.9414471"},{"key":"28_CR24","doi-asserted-by":"publisher","unstructured":"Ueno, S., Mimura, M., Sakai, S., Kawahara, T.: Data augmentation for ASR using TTS via a discrete representation. In: 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Cartagena, Colombia, pp. 68\u201375. IEEE (2021). https:\/\/doi.org\/10.1109\/ASRU51503.2021.9688218. https:\/\/ieeexplore.ieee.org\/document\/9688218\/","DOI":"10.1109\/ASRU51503.2021.9688218"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhang, Y., Halpern, B.M., Patel, T., Scharenborg, O.: Mitigating bias against non-native accents. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, vol. 2022, pp. 3168\u20133172 (2022)","DOI":"10.21437\/Interspeech.2022-836"},{"key":"28_CR26","doi-asserted-by":"publisher","unstructured":"Zhao, G., et al.: L2-arctic: a non-native English speech corpus. In: Proceedings of the Interspeech, pp. 2783\u20132787 (2018). https:\/\/doi.org\/10.21437\/Interspeech.2018-1110","DOI":"10.21437\/Interspeech.2018-1110"},{"key":"28_CR27","doi-asserted-by":"publisher","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: 2021 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, pp. 5674\u20135678 (2021). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9414778. iSSN 2379-190X","DOI":"10.1109\/ICASSP39728.2021.9414778"},{"key":"28_CR28","doi-asserted-by":"publisher","unstructured":"Zhu, H., Wang, L., Zhang, P., Yan, Y.: Multi-accent adaptation based on gate mechanism. In: Interspeech 2019, pp. 744\u2013748. ISCA (2019). https:\/\/doi.org\/10.21437\/Interspeech.2019-3155. https:\/\/www.isca-speech.org\/archive\/interspeech_2019\/zhu19_interspeech.html","DOI":"10.21437\/Interspeech.2019-3155"}],"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\/978-3-031-40498-6_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T23:06:01Z","timestamp":1692745561000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-40498-6_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031404979","9783031404986"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-40498-6_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"23 August 2023","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":"Pilsen","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.kiv.zcu.cz\/tsd2023\/index.php","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":"CMS & back-office system","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"64","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":"31","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":"48% - 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":"2.56","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}