{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T21:17:35Z","timestamp":1757625455604,"version":"3.44.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032025470"},{"type":"electronic","value":"9783032025487"}],"license":[{"start":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:00Z","timestamp":1755820800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:00Z","timestamp":1755820800000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-02548-7_24","type":"book-chapter","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T05:39:49Z","timestamp":1755754789000},"page":"289-298","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Robust Disfluency Labeling in Spontaneous Speech: Insights from Diverse Hungarian Corpora Including Atypical Speakers"],"prefix":"10.1007","author":[{"given":"Yan","family":"Meng","sequence":"first","affiliation":[]},{"given":"P\u00e9ter","family":"Mihajlik","sequence":"additional","affiliation":[]},{"given":"Dalai","family":"Mengke","sequence":"additional","affiliation":[]},{"given":"Katalin","family":"M\u00e1dy","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,22]]},"reference":[{"issue":"1","key":"24_CR1","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1075\/pc.14.1.08war","volume":"14","author":"N Ward","year":"2006","unstructured":"Ward, N.: Non-lexical conversational sounds in American English. Pragmat. Cogn. 14(1), 129\u2013182 (2006)","journal-title":"Pragmat. Cogn."},{"issue":"5","key":"24_CR2","doi-asserted-by":"publisher","first-page":"1526","DOI":"10.1109\/TASL.2006.878255","volume":"14","author":"Y Liu","year":"2006","unstructured":"Liu, Y., Shriberg, E., Stolcke, A., Hillard, D., Ostendorf, M., Harper, M.: Enriching speech recognition with automatic detection of sentence boundaries and disfluencies. IEEE Trans. Audio Speech Lang. Process. 14(5), 1526\u20131540 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"2","key":"24_CR3","doi-asserted-by":"publisher","first-page":"130","DOI":"10.2174\/1567205014666171121114930","volume":"15","author":"L T\u00f3th","year":"2018","unstructured":"T\u00f3th, L., et al.: A speech recognition-based solution for the automatic detection of mild cognitive impairment from spontaneous speech. Curr. Alzheimer Res. 15(2), 130\u2013138 (2018)","journal-title":"Curr. Alzheimer Res."},{"key":"24_CR4","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/j.csl.2018.07.007","volume":"53","author":"G Gosztolya","year":"2019","unstructured":"Gosztolya, G., Vincze, V., T\u00f3th, L., P\u00e1k\u00e1ski, M., K\u00e1lm\u00e1n, J., Hoffmann, I.: Identifying mild cognitive impairment and mild Alzheimer\u2019s disease based on spontaneous speech using ASR and linguistic features. Comput. Speech Lang. 53, 181\u2013197 (2019)","journal-title":"Comput. Speech Lang."},{"issue":"6","key":"24_CR5","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1109\/MSP.2016.2599201","volume":"33","author":"F Weng","year":"2016","unstructured":"Weng, F., Angkititrakul, P., Shriberg, E.E., Heck, L., Peters, S., Hansen, J.H.L.: Conversational in-vehicle dialog systems: the past, present, and future. IEEE Signal Process. Mag. 33(6), 49\u201360 (2016)","journal-title":"IEEE Signal Process. Mag."},{"key":"24_CR6","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1007\/978-3-031-48309-7_16","volume-title":"SPECOM 2023","author":"M Bhattacharjee","year":"2023","unstructured":"Bhattacharjee, M., Baghel, S., Prasanna, S.R.M.: Driver speech detection in real driving scenario. In: Karpov, A., et al. (eds.) SPECOM 2023. LNCS, vol. 14338, pp. 189\u2013199. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-48309-7_16"},{"key":"24_CR7","unstructured":"Scibelli, F.: Detection of verbal and nonverbal speech features as markers of depression: results of manual analysis and automatic classification. Napoli: Universit\u00e0 degli Studi di Napoli Federico II (2019)"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Silber-Varod, V., Kreiner, H., Lovett, R., Levi-Belz, Y., Amir, N.: Do social anxiety individuals hesitate more? The prosodic profile of hesitation disfluencies in social anxiety disorder individuals. In: Proceedings of Speech Prosody 2016, pp. 1211\u20131215 (2016)","DOI":"10.21437\/SpeechProsody.2016-249"},{"key":"24_CR9","unstructured":"Horii, K., Fukuda, M., Ohta, K., Nishimura, R., Ogawa, A., Kitaoka, N.: End-to-end spontaneous speech recognition using hesitation labeling. In: 2021 Asia-Pacific Signal and Information Processing Association ASC, pp. 1077\u20131081. IEEE (2021)"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Horii, K., Fukuda, M., Ohta, K., Nishimura, R., Ogawa, A., Kitaoga, N.: End-to-end spontaneous speech recognition using disfluency labeling. In: Proceedings of Interspeech 2022, pp. 4108\u20134112 (2022)","DOI":"10.21437\/Interspeech.2022-281"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Mihajlik, P., Meng, Y., Kadar, M.S., Linke, J., Schuppler, B., M\u00e1dy, K.: On disfluency and non-lexical sound labeling for end-to-end automatic speech recognition. In: Proceedings of Interspeech 2024, pp. 1270\u20131274 (2024)","DOI":"10.21437\/Interspeech.2024-2157"},{"key":"24_CR12","unstructured":"Mihajlik, P., Balog, A., Gr\u00e1czi, T.E., Koh\u00e1ri, A., Tarj\u00e1n, B., M\u00e1dy, K.: BEA-base: a benchmark for ASR of spontaneous Hungarian. In: Proceedings of the Thirteenth Language Resources and Evaluation Conference, Marseille, France, pp. 1970\u20131977. European Language Resources Association (2022)"},{"issue":"3","key":"24_CR13","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1111\/1556-4029.15250","volume":"68","author":"D Sztah\u00f3","year":"2023","unstructured":"Sztah\u00f3, D., Fejes, A.: Effects of language mismatch in automatic forensic voice comparison using deep learning embeddings. J. Forensic Sci. 68(3), 871\u2013883 (2023)","journal-title":"J. Forensic Sci."},{"key":"24_CR14","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2022.879896","volume":"13","author":"B Hajduska-D\u00e9r","year":"2022","unstructured":"Hajduska-D\u00e9r, B., Kiss, G., Sztah\u00f3, D., Vicsi, K., Simon, L.: The applicability of the beck depression inventory and Hamilton depression scale in the automatic recognition of depression based on speech signal processing. Front. Psych. 13, 879896 (2022)","journal-title":"Front. Psych."},{"key":"24_CR15","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, pp. 12449\u201312460 (2020)"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.: Voxpopuli: a large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation. arXiv preprint arXiv:2101.00390 (2021)","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Mihajlik, P., et al.: What kind of multi- or cross-lingual pre-training is the most effective for a spontaneous, less-resourced ASR task? In: Proceedings of 2nd Annual Meeting of the ELRA\/ISCA SIG on Under-Resourced Languages (SIGUL 2023), pp. 58\u201362 (2023)","DOI":"10.21437\/SIGUL.2023-13"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Mendelev, V., Raissi, T., Camporese, G., Giollo, M.: Improved robustness to disfluencies in RNN-transducer based speech recognition. In: ICASSP 2021, pp. 6878\u20136882. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9413618"},{"key":"24_CR19","unstructured":"Ravanelli, M., et al.: SpeechBrain: a general-purpose speech toolkit (2021). arXiv:2106.04624"},{"key":"24_CR20","unstructured":"Ravanelli, M., et al.: Open-source conversational AI with SpeechBrain 1.0 (2024)"},{"key":"24_CR21","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":"24_CR22","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Park, D.S., et al.: Specaugment: a simple data augmentation method for automatic speech recognition. arXiv preprint arXiv:1904.08779 (2019)","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Kudo, T., Richardson, J.: SentencePiece: a simple and language independent subword tokenizer and detokenizer for neural text processing. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, Brussels, Belgium, pp. 66\u201371. ACL (2018)","DOI":"10.18653\/v1\/D18-2012"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. CoRR, abs\/1508.07909 (2015)","DOI":"10.18653\/v1\/P16-1162"},{"issue":"3","key":"24_CR26","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1109\/MM.2018.032271057","volume":"38","author":"N Jouppi","year":"2018","unstructured":"Jouppi, N., Young, C., Patil, N., Patterson, D.: Motivation for and evaluation of the first tensor processing unit. IEEE Micro 38(3), 10\u201319 (2018)","journal-title":"IEEE Micro"}],"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\/978-3-032-02548-7_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T18:05:19Z","timestamp":1757441119000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-02548-7_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,22]]},"ISBN":["9783032025470","9783032025487"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-02548-7_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,8,22]]},"assertion":[{"value":"22 August 2025","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":"Erlangen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.kiv.zcu.cz\/tsd2025\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}