{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,30]],"date-time":"2026-08-30T21:14:02Z","timestamp":1788124442676,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372482","type":"print"},{"value":"9783032372499","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T00:00:00Z","timestamp":1788134400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T00:00:00Z","timestamp":1788134400000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-37249-9_39","type":"book-chapter","created":{"date-parts":[[2026,8,30]],"date-time":"2026-08-30T20:25:20Z","timestamp":1788121520000},"page":"478-490","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Benchmarking Pretrained Speech Models for\u00a0Arabic Dialect Identification with\u00a0Cross-Corpus Evaluation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3657-1001","authenticated-orcid":false,"given":"Christopher","family":"Simic","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3582-2154","authenticated-orcid":false,"given":"Korbinian","family":"Riedhammer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3502-9511","authenticated-orcid":false,"given":"Sebastian","family":"Bayerl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7780-8821","authenticated-orcid":false,"given":"Tobias","family":"Bocklet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,31]]},"reference":[{"key":"39_CR1","doi-asserted-by":"crossref","unstructured":"Ali, A.M., et al.: Automatic dialect detection in arabic broadcast speech, Interspeech (2015)","DOI":"10.21437\/Interspeech.2016-1297"},{"key":"39_CR2","doi-asserted-by":"crossref","unstructured":"Alvarez, A.A., Issa, E.: Learning intonation pattern embeddings for arabic dialect identification, Interspeech (2020)","DOI":"10.21437\/Interspeech.2020-2906"},{"key":"39_CR3","unstructured":"Baevski, A., Zhou, H., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations, p. NIPS (2020)"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Bayerl, S.P., Wagner, D., Noth, E., Bocklet, T., Riedhammer, K.: The influence of dataset partitioning on dysfluency detection systems, TSD (2022)","DOI":"10.1007\/978-3-031-16270-1_35"},{"key":"39_CR5","doi-asserted-by":"crossref","unstructured":"Biadsy, F., Hirschberg, J., Habash, N.: Spoken arabic dialect identification using phonotactic modeling. In: SEMITIC@EACL (2009)","DOI":"10.3115\/1621774.1621784"},{"key":"39_CR6","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Nagrani, A., Zisserman, A.: VoxCeleb2: deep speaker recognition, Interspeech (2018)","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"39_CR7","doi-asserted-by":"crossref","unstructured":"Desplanques, B., Thienpondt, J., Demuynck, K.: ECAPA-TDNN: emphasized channel attention, propagation and aggregation in TDNN based speaker verification, Interspeech (2020)","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"39_CR8","doi-asserted-by":"crossref","unstructured":"Fan, Z., Li, M., Zhou, S., Xu, B.: Exploring wav2vec 2.0 on speaker verification and language identification, Interspeech (2021)","DOI":"10.21437\/Interspeech.2021-1280"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Kulkarni, A., et al.: Yet another model for Arabic dialect identification. In: Almatham, R. (ed.) ArabicNLP (2023)","DOI":"10.18653\/v1\/2023.arabicnlp-1.37"},{"key":"39_CR10","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Chung, J.S., Zisserman, A.: VoxCeleb: a large-scale speaker identification dataset. In: Interspeech (2017)","DOI":"10.21437\/Interspeech.2017-950"},{"key":"39_CR12","doi-asserted-by":"crossref","unstructured":"Parsons, P., Bremnes, H.S., Kvale, K.A., Svendsen, T., Salvi, G.: Effects of prosodic information on dialect classification using whisper features, Interspeech (2025).","DOI":"10.21437\/Interspeech.2025-200"},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Pepino, L., Riera, P., Ferrer, L.: Emotion recognition from speech using wav2vec 2.0 embeddings, Interspeech (2021)","DOI":"10.21437\/Interspeech.2021-703"},{"key":"39_CR14","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision (2022)"},{"key":"39_CR15","doi-asserted-by":"crossref","unstructured":"Salamon, J., Jacoby, C., Bello, J.P.: A dataset and taxonomy for urban sound research, ACM-MM (2014)","DOI":"10.1145\/2647868.2655045"},{"key":"39_CR16","doi-asserted-by":"crossref","unstructured":"Shon, S., Ali, A., Samih, Y., Mubarak, H., Glass, J.: ADI17: a fine-grained arabic dialect identification dataset. ICASSP (2020)","DOI":"10.1109\/ICASSP40776.2020.9052982"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Simic, C., Bocklet, T.: Self-supervised adaptive av fusion module for pre-trained ASR models. ICASSP. pp, 12787\u201312791 (2024)","DOI":"10.1109\/ICASSP48485.2024.10448047"},{"key":"39_CR18","doi-asserted-by":"crossref","unstructured":"Simic, C., Riedhammer, K., Bocklet, T.: Adapter-based multi-agent AVSR extension for pre-trained asr models. ICASSP. pp, 1\u20135 (2025)","DOI":"10.1109\/ICASSP49660.2025.10889566"},{"key":"39_CR19","unstructured":"Sinisetty, G., Ruban, P., Dymov, O., Ravanelli, M.: Commonlanguage (2021)"},{"key":"39_CR20","doi-asserted-by":"crossref","unstructured":"Spencer, C., Yakymchuk, C., Ghaznavi, M.: Visualising data distributions with kernel density estimation and reduced chi-squared statistic. Geosci. Front (2017)","DOI":"10.1016\/j.gsf.2017.05.002"},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"Talafha, B., et al.: NADI 2025: the first multidialectal Arabic speech processing shared task. In: The Third Arabic Natural Language Processing Conference: Shared Tasks, Association for Computational Linguistics, Suzhou, China (2025)","DOI":"10.18653\/v1\/2025.arabicnlp-sharedtasks.99"},{"key":"39_CR22","doi-asserted-by":"crossref","unstructured":"Valk, J., Alumae, T.: VoxLingua107: A dataset for spoken language recognition. SLT (2020)","DOI":"10.1109\/SLT48900.2021.9383459"}],"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\/978-3-032-37249-9_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,30]],"date-time":"2026-08-30T20:25:21Z","timestamp":1788121521000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37249-9_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,31]]},"ISBN":["9783032372482","9783032372499"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37249-9_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,31]]},"assertion":[{"value":"31 August 2026","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":"Brno","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":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.tsdconference.org\/tsd2026\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}