{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T10:25:23Z","timestamp":1771064723574,"version":"3.50.1"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031162695","type":"print"},{"value":"9783031162701","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-16270-1_41","type":"book-chapter","created":{"date-parts":[[2022,9,15]],"date-time":"2022-09-15T09:30:11Z","timestamp":1663234211000},"page":"501-512","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Evaluation of\u00a0Wav2Vec Speech Recognition for\u00a0Speakers with\u00a0Cognitive Disorders"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8362-5927","authenticated-orcid":false,"given":"Jan","family":"\u0160vec","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Filip","family":"Pol\u00e1k","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8020-8252","authenticated-orcid":false,"given":"Ale\u0161","family":"Barto\u0161","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5041-8865","authenticated-orcid":false,"given":"Michaela","family":"Zapletalov\u00e1","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2466-3998","authenticated-orcid":false,"given":"Martin","family":"V\u00edta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,9,16]]},"reference":[{"key":"41_CR1","doi-asserted-by":"publisher","first-page":"18183","DOI":"10.1109\/ACCESS.2021.3053335","volume":"9","author":"BA Al-Qatab","year":"2021","unstructured":"Al-Qatab, B.A., Mustafa, M.B.: Classification of dysarthric speech according to the severity of impairment: an analysis of acoustic features. IEEE Access 9, 18183\u201318194 (2021). https:\/\/doi.org\/10.1109\/ACCESS.2021.3053335","journal-title":"IEEE Access"},{"key":"41_CR2","doi-asserted-by":"crossref","unstructured":"Baevski, A., Rahman Mohamed, A.: Effectiveness of self-supervised pre-training for ASR. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7694\u20137698 (2020)","DOI":"10.1109\/ICASSP40776.2020.9054224"},{"key":"41_CR3","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, 33, pp. 12449\u201312460 (2020)"},{"issue":"6","key":"41_CR4","first-page":"671","volume":"112","author":"A Barto\u0161","year":"2016","unstructured":"Barto\u0161, A.: Netestuj, ale pobav - p\u00edsemn\u00e9 z\u00e1m\u011brn\u00e9 pojmenov\u00e1n\u00ed obr\u00e1zk\u016f a jejich vybaven\u00ed jako kr\u00e1tk\u00e1 kognitivn\u00ed zkou\u0161ka. Cesko Slov Neurol N. 112(6), 671\u2013679 (2016)","journal-title":"Cesko Slov Neurol N."},{"key":"41_CR5","unstructured":"Barto\u0161, A.: Netestuj, ale pobav - p\u00edsemn\u00e9 z\u00e1m\u0161rn\u00e9 pojmenov\u00e1n\u00ed obr\u00e1zk\u016f a jejich vybaven\u00ed jako kr\u00e1tk\u00e1 kognitivn\u00ed zkou\u0161ka. Cesko Slov Neurol N. 82(4), 369\u2013378 (2019)"},{"key":"41_CR6","unstructured":"Baskar, M.K., Herzig, T., Nguyen, D., Diez, M., Polzehl, T., Burget, L., \u010cernock\u00fd, J.H.: Speaker adaptation for wav2vec2 based dysarthric ASR (2022). arXiv preprint arXiv: 2204.00770"},{"issue":"1","key":"41_CR7","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1186\/s13195-019-0474-3","volume":"11","author":"EE De Roeck","year":"2019","unstructured":"De Roeck, E.E., De Deyn, P.P., Dierckx, E., Engelborghs, S.: Brief cognitive screening instruments for early detection of Alzheimer\u2019s disease: a systematic review. Alzheimer\u2019s Res. Ther. 11(1), 21 (2019). https:\/\/doi.org\/10.1186\/s13195-019-0474-3","journal-title":"Alzheimer\u2019s Res. Ther."},{"key":"41_CR8","doi-asserted-by":"crossref","unstructured":"Lehe\u010dka, J., \u0160vec, J., A.P., Psutka, J.: Exploring capabilities of monolingual audio transformers using large datasets in automatic speech recognition of Czech. In: Proceedings Interspeech (2022)","DOI":"10.21437\/Interspeech.2022-10439"},{"key":"41_CR9","doi-asserted-by":"publisher","unstructured":"K\u00f6nig, A., et al.: Automatic speech analysis for the assessment of patients with predementia and alzheimer\u2019s disease. Alzheimer\u2019s Dementia Diagn. Assessment Dis. Monit. 1(1), 112\u2013124 (2015). https:\/\/doi.org\/10.1016\/j.dadm.2014.11.012, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S2352872915000160","DOI":"10.1016\/j.dadm.2014.11.012"},{"key":"41_CR10","doi-asserted-by":"publisher","unstructured":"Luz, S., Haider, F., de la Fuente, S., Fromm, D., MacWhinney, B.: Detecting cognitive decline using speech only: the ADReSSo challenge. In: Proceedings Interspeech 2021, pp. 3780\u20133784 (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-1220","DOI":"10.21437\/Interspeech.2021-1220"},{"key":"41_CR11","unstructured":"Pra\u017e\u00e1k, A., Loose, Z., Psutka, J.V., Radov\u00e1, V., Psutka, J., \u0160vec, J.: Live tv subtitling through respeaking. In: INTERSPEECH 2021, pp. 2339\u20132340 (2021)"},{"key":"41_CR12","doi-asserted-by":"publisher","unstructured":"Pulido, M.L.B., et al.: Alzheimer\u2019s disease and automatic speech analysis: a review. Expert Syst. Appl. 150, 113213 (2020). https:\/\/doi.org\/10.1016\/j.eswa.2020.113213, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0957417420300397","DOI":"10.1016\/j.eswa.2020.113213"},{"key":"41_CR13","doi-asserted-by":"publisher","first-page":"211","DOI":"10.3233\/JAD-191056","volume":"75","author":"Y Qiao","year":"2020","unstructured":"Qiao, Y.: Computer-assisted speech analysis in mild cognitive impairment and alzheimer\u2019s disease: a pilot study from shanghai, China. J. Alzheimer\u2019s Dis. 75, 211\u2013221 (2020). https:\/\/doi.org\/10.3233\/JAD-191056","journal-title":"J. Alzheimer\u2019s Dis."},{"key":"41_CR14","doi-asserted-by":"publisher","unstructured":"Ren, J., Liu, M.: An automatic dysarthric speech recognition approach using deep neural networks. Int. J. Adv. Comput. Sci. Appl. 8(12) (2017). https:\/\/doi.org\/10.14569\/IJACSA.2017.081207","DOI":"10.14569\/IJACSA.2017.081207"},{"key":"41_CR15","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1007\/978-3-319-64206-2_57","volume-title":"Text, Speech, and Dialogue","author":"P Stanislav","year":"2017","unstructured":"Stanislav, P., Psutka, J.V., Psutka, J.: Recognition of the electrolaryngeal speech: comparison between human and machine. In: Ek\u0161tein, K., Matou\u0161ek, V. (eds.) TSD 2017. LNCS (LNAI), vol. 10415, pp. 509\u2013517. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-64206-2_57"},{"key":"41_CR16","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1007\/978-3-030-00794-2_40","volume-title":"Text, Speech, and Dialogue","author":"D Tihelka","year":"2018","unstructured":"Tihelka, D., Hanzl\u00ed\u010dek, Z., J\u016fzov\u00e1, M., V\u00edt, J., Matou\u0161ek, J., Gr\u016fber, M.: Current state of text-to-speech system ARTIC: a\u00a0decade of research on the field of speech technologies. In: Sojka, P., Hor\u00e1k, A., Kope\u010dek, I., Pala, K. (eds.) TSD 2018. LNCS (LNAI), vol. 11107, pp. 369\u2013378. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00794-2_40"},{"key":"41_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1007\/978-3-030-33904-3_66","volume-title":"Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications","author":"J V\u00e1squez-Correa","year":"2019","unstructured":"V\u00e1squez-Correa, J., et al.: Convolutional neural networks and a transfer learning strategy to classify Parkinson\u2019s disease from speech in three different languages. In: Nystr\u00f6m, I., Hern\u00e1ndez Heredia, Y., Mili\u00e1n N\u00fa\u00f1ez, V. (eds.) CIARP 2019. LNCS, vol. 11896, pp. 697\u2013706. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-33904-3_66"},{"key":"41_CR18","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"41_CR19","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.: VoxPopuli: a large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation. In: Proceedings of ACL (Volume 1: Long Papers), pp. 993\u20131003. Association for Computational Linguistics, (2021). https:\/\/aclanthology.org\/2021.acl-long.80","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"41_CR20","doi-asserted-by":"crossref","unstructured":"Weiner, J., Herff, C., Schultz, T.: Speech-based detection of Alzheimer\u2019s disease in conversational German. In: Interspeech, pp. 1938\u20131942 (2016)","DOI":"10.21437\/Interspeech.2016-100"},{"key":"41_CR21","doi-asserted-by":"publisher","unstructured":"Yadav, V.G.: The hunt for a cure for Alzheimer\u2019s disease receives a timely boost. Sci. Transl. Med. 11(509), eaaz0311 (2019). https:\/\/doi.org\/10.1126\/scitranslmed.aaz0311, https:\/\/www.science.org\/doi\/abs\/10.1126\/scitranslmed.aaz0311","DOI":"10.1126\/scitranslmed.aaz0311"},{"key":"41_CR22","doi-asserted-by":"publisher","unstructured":"Zhu, Y., Obyat, A., Liang, X., Batsis, J.A., Roth, R.M.: WavBERT: exploiting semantic and non-semantic speech using Wav2vec and BERT for dementia detection. In: Proceedings Interspeech 2021, pp. 3790\u20133794 (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-332","DOI":"10.21437\/Interspeech.2021-332"},{"key":"41_CR23","doi-asserted-by":"crossref","unstructured":"\u0160vec, J., Neduchal, P., Hr\u00faz, M.: Multi-modal communication system for mobile robot. In: Proceedings of 17th International Conference on Programmable Devices and Embedded Systems, PDeS 2022 (2022)","DOI":"10.1016\/j.ifacol.2022.06.022"}],"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\/978-3-031-16270-1_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,19]],"date-time":"2023-02-19T05:29:12Z","timestamp":1676784552000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16270-1_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031162695","9783031162701"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16270-1_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"16 September 2022","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2022","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":"tsd2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.tsdconference.org\/tsd2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}