{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T10:45:39Z","timestamp":1775040339074,"version":"3.50.1"},"publisher-location":"Cham","reference-count":14,"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_42","type":"book-chapter","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:03:21Z","timestamp":1700597001000},"page":"529-538","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["End-to-End Native Language Identification Using a\u00a0Modified Vision Transformer(ViT) from\u00a0L2 English Speech"],"prefix":"10.1007","author":[{"given":"Kishan","family":"Pipariya","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Debolina","family":"Pramanik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Puja","family":"Bharati","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sabyasachi","family":"Chandra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shyamal Kumar Das","family":"Mandal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"key":"42_CR1","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"42_CR2","doi-asserted-by":"crossref","unstructured":"Gong, Y., Chung, Y.A., Glass, J.: AST: audio spectrogram transformer. arXiv preprint arXiv:2104.01778 (2021)","DOI":"10.21437\/Interspeech.2021-698"},{"key":"42_CR3","doi-asserted-by":"crossref","unstructured":"Gong, Y., Lai, C.I., Chung, Y.A., Glass, J.: SSAST: self-supervised audio spectrogram transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 10699\u201310709 (2022)","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"42_CR4","doi-asserted-by":"crossref","unstructured":"Graham, C.: L1 identification from L2 speech using neural spectrogram analysis. In: Interspeech, vol. 2021, pp. 3959\u20133963 (2021)","DOI":"10.21437\/Interspeech.2021-1545"},{"issue":"6","key":"42_CR5","doi-asserted-by":"publisher","first-page":"3487","DOI":"10.1007\/s00034-021-01948-7","volume":"41","author":"RK Guntur","year":"2022","unstructured":"Guntur, R.K., Ramakrishnan, K., Vinay Kumar, M.: An automated classification system based on regional accent. Circuits Syst. Signal Process 41(6), 3487\u20133507 (2022)","journal-title":"Circuits Syst. Signal Process"},{"key":"42_CR6","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.specom.2022.03.007","volume":"139","author":"MA Humayun","year":"2022","unstructured":"Humayun, M.A., Yassin, H., Abas, P.E.: Native language identification for Indian-speakers by an ensemble of phoneme-specific, and text-independent convolutions. Speech Commun. 139, 92\u2013101 (2022)","journal-title":"Speech Commun."},{"key":"42_CR7","doi-asserted-by":"crossref","unstructured":"Jiao, Y., Tu, M., Berisha, V., Liss, J.M.: Accent identification by combining deep neural networks and recurrent neural networks trained on long and short term features. In: Interspeech, pp. 2388\u20132392 (2016)","DOI":"10.21437\/Interspeech.2016-1148"},{"key":"42_CR8","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1007\/978-3-030-60276-5_27","volume-title":"Speech and Computer","author":"L K\u00fcrzinger","year":"2020","unstructured":"K\u00fcrzinger, L., Winkelbauer, D., Li, L., Watzel, T., Rigoll, G.: CTC-Segmentation of large corpora for German end-to-end speech recognition. In: Karpov, A., Potapova, R. (eds.) SPECOM 2020. LNCS (LNAI), vol. 12335, pp. 267\u2013278. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-60276-5_27"},{"key":"42_CR9","doi-asserted-by":"crossref","unstructured":"Rajpal, A., Patel, T.B., Sailor, H.B., Madhavi, M.C., Patil, H.A., Fujisaki, H.: Native language identification using spectral and source-based features. In: Interspeech, pp. 2383\u20132387 (2016)","DOI":"10.21437\/Interspeech.2016-1100"},{"key":"42_CR10","doi-asserted-by":"crossref","unstructured":"Schuller, B., et al.: The interspeech 2016 computational paralinguistics challenge: Deception, sincerity & native language. In: 17TH Annual Conference of the International Speech Communication Association (Interspeech 2016), Vols. 1\u20135, vol. 8, pp. 2001\u20132005. ISCA (2016)","DOI":"10.21437\/Interspeech.2016-129"},{"key":"42_CR11","doi-asserted-by":"crossref","unstructured":"Ubale, R., Qian, Y., Evanini, K.: Exploring end-to-end attention-based neural networks for native language identification. In: 2018 IEEE Spoken Language Technology Workshop (SLT), pp. 84\u201391. IEEE (2018)","DOI":"10.1109\/SLT.2018.8639689"},{"key":"42_CR12","doi-asserted-by":"crossref","unstructured":"Ubale, R., Ramanarayanan, V., Qian, Y., Evanini, K., Leong, C.W., Lee, C.M.: Native language identification from raw waveforms using deep convolutional neural networks with attentive pooling. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 403\u2013410. IEEE (2019)","DOI":"10.1109\/ASRU46091.2019.9003872"},{"key":"42_CR13","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1007\/978-3-030-60276-5_62","volume-title":"Speech and Computer","author":"T Watzel","year":"2020","unstructured":"Watzel, T., K\u00fcrzinger, L., Li, L., Rigoll, G.: Synchronized forward-backward transformer for end-to-end speech recognition. In: Karpov, A., Potapova, R. (eds.) SPECOM 2020. LNCS (LNAI), vol. 12335, pp. 646\u2013656. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-60276-5_62"},{"key":"42_CR14","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"795","DOI":"10.1007\/978-3-030-87802-3_71","volume-title":"Speech and Computer","author":"T Watzel","year":"2021","unstructured":"Watzel, T., K\u00fcrzinger, L., Li, L., Rigoll, G.: Induced local attention for transformer models in speech recognition. In: Karpov, A., Potapova, R. (eds.) SPECOM 2021. LNCS (LNAI), vol. 12997, pp. 795\u2013806. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87802-3_71"}],"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_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:09:20Z","timestamp":1700597360000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-48312-7_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031483110","9783031483127"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-48312-7_42","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)"}}]}}