{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T23:35:07Z","timestamp":1772753707872,"version":"3.50.1"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031483110","type":"print"},{"value":"9783031483127","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\/978-3-031-48312-7_5","type":"book-chapter","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:03:21Z","timestamp":1700597001000},"page":"59-70","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["CAPTuring Accents: An Approach to\u00a0Personalize Pronunciation Training for\u00a0Learners with\u00a0Different L1 Backgrounds"],"prefix":"10.1007","author":[{"given":"Veronica","family":"Khaustova","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evgeny","family":"Pyshkin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Victor","family":"Khaustov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Blake","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Natalia","family":"Bogach","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Aryal, S., Gutierrez-Osuna, R.: Can voice conversion be used to reduce non-native accents? In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7879\u20137883. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6855134"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Babu, A., et al.: Xls-r: self-supervised cross-lingual speech representation learning at scale. arXiv preprint arXiv:2111.09296 (2021)","DOI":"10.21437\/Interspeech.2022-143"},{"key":"5_CR3","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. Adv. Neural Inf. Process. Syst. 33, 12449\u201312460 (2020)"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Bogach, N., et al.: Speech processing for language learning: a practical approach to computer-assisted pronunciation teaching. Electronics 10(3), 235 (2021)","DOI":"10.3390\/electronics10030235"},{"key":"5_CR5","doi-asserted-by":"publisher","unstructured":"Chakraborty, J., Sinha, R., Sarmah, P.: Influence of accented speech in automatic speech recognition: a case study on Assamese L1 speakers speaking code switched Hindi-English. In: Prasanna, S.R.M., Karpov, A., Samudravijaya, K., Agrawal, S.S. (eds.) Speech and Computer: 24th International Conference, SPECOM 2022, Gurugram, India, 14\u201316 November 2022, Proceedings, pp. 87\u201398. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20980-2_9","DOI":"10.1007\/978-3-031-20980-2_9"},{"issue":"10","key":"5_CR6","doi-asserted-by":"publisher","first-page":"920","DOI":"10.1016\/j.specom.2008.11.004","volume":"51","author":"D Felps","year":"2009","unstructured":"Felps, D., Bortfeld, H., Gutierrez-Osuna, R.: Foreign accent conversion in computer assisted pronunciation training. Speech Commun. 51(10), 920\u2013932 (2009)","journal-title":"Speech Commun."},{"key":"5_CR7","unstructured":"George Mason University. Speech accent archive (2021). https:\/\/accent.gmu.edu\/"},{"key":"5_CR8","unstructured":"Gilbert, J.B.: Teaching Pronunciation: Using the Prosody Pyramid. Cambridge University Press (2008)"},{"key":"5_CR9","unstructured":"Gondi, S.: Wav2vec2. 0 on the edge: Performance evaluation. arXiv preprint arXiv:2202.05993 (2022)"},{"key":"5_CR10","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":"5_CR11","doi-asserted-by":"crossref","unstructured":"Ishikawa, S.: The ICNALE Guide: An Introduction to a Learner Corpus Study on Asian Learners\u2019 L2 English. Taylor & Francis (2023)","DOI":"10.4324\/9781003252528"},{"issue":"4","key":"5_CR12","first-page":"393","volume":"9","author":"S Karpagavalli","year":"2016","unstructured":"Karpagavalli, S., Chandra, E.: A review on automatic speech recognition architecture and approaches. Int. J. Signal Process. Image Process. Pattern Recogn. 9(4), 393\u2013404 (2016)","journal-title":"Int. J. Signal Process. Image Process. Pattern Recogn."},{"key":"5_CR13","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/978-981-16-0115-6_5","volume":"6","author":"D Liu","year":"2021","unstructured":"Liu, D., Reed, M.: Exploring the complexity of the l2 intonation system: an acoustic and eye-tracking study. Front. Commun. 6, 51 (2021)","journal-title":"Front. Commun."},{"issue":"16","key":"5_CR14","doi-asserted-by":"publisher","first-page":"2913","DOI":"10.3390\/math10162913","volume":"10","author":"V Mikhailava","year":"2022","unstructured":"Mikhailava, V., Lesnichaia, M., Bogach, N., Lezhenin, I., Blake, J., Pyshkin, E.: Language accent detection with CNN using sparse data from a crowd-sourced speech archive. Mathematics 10(16), 2913 (2022)","journal-title":"Mathematics"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Mikhailava, V., et al.: Tailoring computer-assisted pronunciation teaching: mixing and matching the mode and manner of feedback to learners. In: INTED2022 Proceedings, pp. 767\u2013773. IATED (2022)","DOI":"10.21125\/inted.2022.0263"},{"key":"5_CR16","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.specom.2017.01.008","volume":"88","author":"SH Mohammadi","year":"2017","unstructured":"Mohammadi, S.H., Kain, A.: An overview of voice conversion systems. Speech Commun. 88, 65\u201382 (2017)","journal-title":"Speech Commun."},{"issue":"1","key":"5_CR17","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1111\/j.1467-1770.1995.tb00963.x","volume":"45","author":"MJ Munro","year":"1995","unstructured":"Munro, M.J., Derwing, T.M.: Foreign accent, comprehensibility, and intelligibility in the speech of second language learners. Lang. Learn. 45(1), 73\u201397 (1995)","journal-title":"Lang. Learn."},{"key":"5_CR18","unstructured":"Murphy, V.A.: Second language learning in the early school years: trends and contexts. Oxford University Press (2014)"},{"key":"5_CR19","unstructured":"Paszke, A.E.A.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32, pp. 8024\u20138035. Curran Associates, Inc. (2019)"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Pennington, M.C., Rogerson-Revell, P.: English Pronunciation Teaching and Research, vol. 10, pp. 978\u2013988. Palgrave Macmillan, Londres (2019)","DOI":"10.1057\/978-1-137-47677-7"},{"key":"5_CR21","doi-asserted-by":"publisher","unstructured":"Permanasari, Y., Harahap, E.H., Ali, E.P.: Speech recognition using dynamic time warping (DTW). J. Phys. Conf. Ser. 1366, 012091 (2019). https:\/\/doi.org\/10.1088\/1742-6596\/1366\/1\/012091. IOP Publishing","DOI":"10.1088\/1742-6596\/1366\/1\/012091"},{"issue":"1","key":"5_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13636-021-00199-3","volume":"2021","author":"K Radzikowski","year":"2021","unstructured":"Radzikowski, K., Wang, L., Yoshie, O., Nowak, R.: Accent modification for speech recognition of non-native speakers using neural style transfer. EURASIP J. Audio Speech Music Process. 2021(1), 1\u201310 (2021)","journal-title":"EURASIP J. Audio Speech Music Process."},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Rilliard, A., Allauzen, A., Boula_de_Mare\u00fcil, P.: Using dynamic time warping to compute prosodic similarity measures. In: Twelfth Annual Conference of the International Speech Communication Association (2011)","DOI":"10.21437\/Interspeech.2011-531"},{"issue":"1","key":"5_CR24","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1177\/0033688220977406","volume":"52","author":"PM Rogerson-Revell","year":"2021","unstructured":"Rogerson-Revell, P.M.: Computer-assisted pronunciation training (CAPT): current issues and future directions. RELC J. 52(1), 189\u2013205 (2021)","journal-title":"RELC J."},{"key":"5_CR25","doi-asserted-by":"publisher","unstructured":"Sullivan, P., Shibano, T., Abdul-Mageed, M.: Improving automatic speech recognition for non-native English with transfer learning and language model decoding. In: Analysis and Application of Natural Language and Speech Processing, pp. 21\u201344. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-11035-1_2","DOI":"10.1007\/978-3-031-11035-1_2"},{"issue":"4","key":"5_CR26","doi-asserted-by":"publisher","first-page":"1743","DOI":"10.26637\/MJM0804\/0070","volume":"8","author":"RK Thandil","year":"2020","unstructured":"Thandil, R.K., Basheer, K.M.: Accent based speech recognition: a critical overview. Malaya J. Matemat. 8(4), 1743\u20131750 (2020)","journal-title":"Malaya J. Matemat."},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Viglino, T., Motlicek, P., Cernak, M.: End-to-end accented speech recognition. In: Interspeech, pp. 2140\u20132144 (2019)","DOI":"10.21437\/Interspeech.2019-2122"},{"key":"5_CR28","unstructured":"Wolf, T., et al.: Huggingface\u2019s transformers: state-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019)"},{"key":"5_CR29","doi-asserted-by":"crossref","unstructured":"Zhao, G., et al.: L2-arctic: a non-native English speech corpus. In: Interspeech, pp. 2783\u20132787 (2018)","DOI":"10.21437\/Interspeech.2018-1110"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-48312-7_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:04:01Z","timestamp":1700597041000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-48312-7_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031483110","9783031483127"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-48312-7_5","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":"22 November 2023","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":"Dharwad","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"29 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iitdh.ac.in\/specom-2023\/","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":"174","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":"94","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":"54% - 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":"4","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)"}}]}}