{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T03:00:10Z","timestamp":1773284410054,"version":"3.50.1"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032025470","type":"print"},{"value":"9783032025487","type":"electronic"}],"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_6","type":"book-chapter","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T05:39:05Z","timestamp":1755754745000},"page":"60-71","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Audio\u2013Vision Contrastive Learning for\u00a0Phonological Class Recognition"],"prefix":"10.1007","author":[{"given":"Daiqi","family":"Liu","sequence":"first","affiliation":[]},{"given":"Tom\u00e1s","family":"Arias-Vergara","sequence":"additional","affiliation":[]},{"given":"Jana","family":"Hutter","sequence":"additional","affiliation":[]},{"given":"Andreas","family":"Maier","sequence":"additional","affiliation":[]},{"given":"Paula Andrea","family":"P\u00e9rez-Toro","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,22]]},"reference":[{"key":"6_CR1","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1016\/j.csl.2020.101130","volume":"65","author":"MH Franciscatto","year":"2021","unstructured":"Franciscatto, M.H., et al.: Towards a speech therapy support system based on phonological processes early detection. Comput. Speech Lang. 65, 101\u2013130 (2021)","journal-title":"Comput. Speech Lang."},{"key":"6_CR2","doi-asserted-by":"publisher","first-page":"e6","DOI":"10.1017\/ATSIP.2016.5","volume":"5","author":"A Toutios","year":"2016","unstructured":"Toutios, A., Narayanan, S.S.: Advances in real-time magnetic resonance imaging of the vocal tract for speech science and technology research. APSIPA Trans. Signal Inf. Process. 5, e6 (2016)","journal-title":"APSIPA Trans. Signal Inf. Process."},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Aleksic, P.S., Potamianos, G., Katsaggelos, A.K.: Audiovisual speech processing. In: The Essential Guide to Video Processing, pp. 689\u2013737. Elsevier Inc. (2009)","DOI":"10.1016\/B978-0-12-374456-2.00024-4"},{"issue":"3","key":"6_CR4","doi-asserted-by":"publisher","first-page":"1307","DOI":"10.1121\/1.4890284","volume":"136","author":"S Narayanan","year":"2014","unstructured":"Narayanan, S., et al.: Real-time magnetic resonance imaging and electromagnetic articulography database for speech production research (TC). J. Acoust. Soc. Am. 136(3), 1307\u20131311 (2014)","journal-title":"J. Acoust. Soc. Am."},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Saha, P., Srungarapu, P., Fels, S.: Towards automatic speech identification from vocal tract shape dynamics in real-time MRI. arXiv preprint arXiv:1807.11089 (2018)","DOI":"10.21437\/Interspeech.2018-2537"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Van\u00a0Leeuwen, K.G., et\u00a0al.: CNN-based phoneme classifier from vocal tract MRI learns embedding consistent with articulatory topology. In: Interspeech, pp. 909\u2013913 (2019)","DOI":"10.21437\/Interspeech.2019-1173"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Pandey, L., Arif, A.S.: Silent speech and emotion recognition from vocal tract shape dynamics in real-time MRI. In: ACM SIGGRAPH 2021 Posters, pp. 1\u20132 (2021)","DOI":"10.1145\/3450618.3469176"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Qiang, C., et al.: Learning speech representation from contrastive token-acoustic pretraining. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 10196\u201310200. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10447797"},{"key":"6_CR9","unstructured":"Fu, L., et al.: SCaLa: supervised contrastive learning for end-to-end automatic speech recognition. arXiv preprint arXiv:2110.04187, vol. 1 (2021)"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Arias-Vergara, T., et\u00a0al.: Contrastive learning approach for assessment of phonological precision in patients with tongue cancer using MRI data. In: Interspeech, vol. 2024, p. 927 (2024)","DOI":"10.21437\/Interspeech.2024-2236"},{"key":"6_CR11","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"6_CR12","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":"6_CR13","doi-asserted-by":"crossref","unstructured":"tom Dieck, T., N\u00f6th, E., Klumpp, P.: Wav2vec behind the scenes: how end2end models learn phonetics (2022)","DOI":"10.21437\/Interspeech.2022-10865"},{"key":"6_CR14","unstructured":"Narayanan, S., et\u00a0al.: USC-TIMIT: a database of multimodal speech production data. Technical report, USC (2013). http:\/\/sail.usc.edu\/span\/usc-timit"},{"key":"6_CR15","unstructured":"Klumpp, P., Arias-Vergara, T., P\u00e9rez-Toro, P.A., N\u00f6th, E., Orozco-Arroyave, J.R.: Common phone: a multilingual dataset for robust acoustic modelling. arXiv preprint arXiv:2201.05912 (2022)"},{"key":"6_CR16","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"issue":"4","key":"6_CR17","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1016\/S0030-6665(05)70238-3","volume":"33","author":"J Jiang","year":"2000","unstructured":"Jiang, J., Lin, E., Hanson, D.G.: Vocal fold physiology. Otolaryngol. Clin. North Am. 33(4), 699\u2013718 (2000)","journal-title":"Otolaryngol. Clin. North Am."}],"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_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T18:05:10Z","timestamp":1757441110000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-02548-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,22]]},"ISBN":["9783032025470","9783032025487"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-02548-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"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"}}]}}