{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T22:23:53Z","timestamp":1743027833402,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031780134"},{"type":"electronic","value":"9783031780141"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-78014-1_2","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T12:24:05Z","timestamp":1732191845000},"page":"18-29","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automatic Assessment of\u00a0Signs of\u00a0Alcohol Dependency Syndrome from\u00a0Spontaneous Speech"],"prefix":"10.1007","author":[{"given":"G\u00e1bor","family":"Gosztolya","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andr\u00e1s Bence","family":"L\u00e1z\u00e1r","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ildik\u00f3","family":"Hoffmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ot\u00edlia","family":"Bagi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fruzsina Fanni","family":"Farkas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Janka","family":"Gajdics","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"L\u00e1szl\u00f3","family":"T\u00f3th","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J\u00e1nos","family":"K\u00e1lm\u00e1n","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Babu, A., et al.: XLS-R: self-supervised cross-lingual speech representation learning at scale. In: Proceedings of Interspeech, pp. 2278\u20132282 (2022)","DOI":"10.21437\/Interspeech.2022-143"},{"key":"2_CR2","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. Adv. Neural Inf. Process. Syst. 33, 12449\u201312460 (2020)"},{"issue":"2","key":"2_CR3","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1016\/j.csl.2012.09.004","volume":"28","author":"D Bone","year":"2014","unstructured":"Bone, D., Li, M., Black, M.P., Narayanan, S.S.: Intoxicated speech detection: a fusion framework with speaker-normalized hierarchical functionals and GMM supervectors. Comput. Speech Lang. 28(2), 375\u2013391 (2014). https:\/\/doi.org\/10.1016\/j.csl.2012.09.004","journal-title":"Comput. Speech Lang."},{"issue":"17","key":"2_CR4","doi-asserted-by":"publisher","first-page":"2684","DOI":"10.3390\/electronics11172684","volume":"11","author":"HA Carvajal-Casta\u00f1o","year":"2022","unstructured":"Carvajal-Casta\u00f1o, H.A., P\u00e9rez-Toro, P.A., Orozco-Arroyave, J.R.: Classification of Parkinson\u2019s disease patients - a deep learning strategy. Electronics 11(17), 2684 (2022). https:\/\/doi.org\/10.3390\/electronics11172684","journal-title":"Electronics"},{"key":"2_CR5","unstructured":"Cawley, G.C., Talbot, N.L.C.: On over-fitting in model selection and subsequent selection bias in performance evaluation. J. Mach. Learn. Res. 11(Jul), 2079\u20132107 (2010)"},{"issue":"3","key":"2_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 1\u201327 (2011)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"issue":"6","key":"2_CR7","doi-asserted-by":"publisher","first-page":"781","DOI":"10.1037\/neu0000555","volume":"33","author":"KE Courtney","year":"2020","unstructured":"Courtney, K.E., Li, I., Tapert, S.F.: The effect of alcohol use on neuroimaging correlates of cognitive and emotional processing in human adolescence. Neuropsychology 33(6), 781\u2013794 (2020). https:\/\/doi.org\/10.1037\/neu0000555","journal-title":"Neuropsychology"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Egas-L\u00f3pez, J.V., et al.: Automatic screening of mild cognitive impairment and Alzheimer\u2019s disease by means of posterior-thresholding hesitation representation. Comput. Speech Lang. 75(Sep), 101377 (2022)","DOI":"10.1016\/j.csl.2022.101377"},{"issue":"2","key":"2_CR9","doi-asserted-by":"publisher","first-page":"109","DOI":"10.4103\/amh.amh_145_22","volume":"24","author":"AR Endreddy","year":"2023","unstructured":"Endreddy, A.R., Lakshmi, R.C., Seshamma, V.V.: A prospective study of amelioration of cognitive functions following alcohol abstinence in patients with alcohol dependence syndrome. Arch. Ment. Health 24(2), 109\u2013114 (2023). https:\/\/doi.org\/10.4103\/amh.amh_145_22","journal-title":"Arch. Ment. Health"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Fan, Z., Li, M., Zhou, S., Xu, B.: Exploring wav2vec 2.0 on speaker verification and language identification. In: Proceedings of Interspeech, pp. 1509\u20131513 (2021)","DOI":"10.21437\/Interspeech.2021-1280"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Gosztolya, G., T\u00f3th, L., Svindt, V., B\u00f3na, J., Hoffmann, I.: Using acoustic deep neural network embeddings to detect multiple sclerosis from speech. In: Proceedings of ICASSP, pp. 6927\u20136931. Singapore (2022)","DOI":"10.1109\/ICASSP43922.2022.9746856"},{"key":"2_CR12","unstructured":"Grosman, J.: Fine-tuned XLSR-53 large model for speech recognition in Hungarian. https:\/\/huggingface.co\/jonatasgrosman\/wav2vec2-large-xlsr-53-hungarian (2021)"},{"key":"2_CR13","doi-asserted-by":"publisher","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. Psychiatry 13, 879896 (2022). https:\/\/doi.org\/10.3389\/fpsyt.2022.879896","DOI":"10.3389\/fpsyt.2022.879896"},{"issue":"10","key":"2_CR14","doi-asserted-by":"publisher","first-page":"781","DOI":"10.3126\/ajms.v14i10.53860","volume":"14","author":"V Kandasamy","year":"2023","unstructured":"Kandasamy, V., Abdul Rahuman, M., Ramanujam, G.: A study of cognitive impairment and its neuroimaging correlates in patients with alcohol dependence a cross-sectional study. Asian J. Med. Sci. 14(10), 781\u2013794 (2023). https:\/\/doi.org\/10.3126\/ajms.v14i10.53860","journal-title":"Asian J. Med. Sci."},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Klumpp, P., et al.: The phonetic footprint of Parkinson\u2019s disease. Comput. Speech Lang. 72(Mar), 101321 (2022)","DOI":"10.1016\/j.csl.2021.101321"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Kung, J., et al.: Semantic and phonemic fluency in alcohol dependent individuals. In: Proceedings of 51st Annual Meeting of INS, pp.\u00a0799. San Diego, CA, USA (2023)","DOI":"10.1017\/S135561772300992X"},{"key":"2_CR17","doi-asserted-by":"publisher","unstructured":"Laptev, P., Litovkin, S., Kostyuchenko, E.: Determining alcohol intoxication based on speech and neural networks. In: Proceedings of SPECOM, pp. 107\u2013115. Gurugram, India (2023). https:\/\/doi.org\/10.1007\/978-3-031-48309-7_9","DOI":"10.1007\/978-3-031-48309-7_9"},{"issue":"1","key":"2_CR18","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1214\/aoms\/1177730491","volume":"18","author":"HB Mann","year":"1947","unstructured":"Mann, H.B., Whitney, D.R.: On a test of whether one of two random variables is stochastically larger than the other. Ann. Math. Stat. 18(1), 50\u201360 (1947)","journal-title":"Ann. Math. Stat."},{"key":"2_CR19","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 LREC, pp. 1970\u20131977. Marseille, France (2022)"},{"key":"2_CR20","doi-asserted-by":"publisher","unstructured":"Pepino, L., Riera, P., Ferrer, L.: Emotion recognition from speech using wav2vec 2.0 embeddings. In: Proceedings of Interspeech, pp. 3400\u20133404. Brno, Czechia (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-703","DOI":"10.21437\/Interspeech.2021-703"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"P\u00e9rez-Toro, P., et al.: Alzheimer\u2019s detection from English to Spanish using acoustic and linguistic embeddings. In: Proceedings of Interspeech, pp. 2483\u20132487 (2022)","DOI":"10.21437\/Interspeech.2022-10883"},{"key":"2_CR22","doi-asserted-by":"publisher","unstructured":"P\u00e9rez-Toro, P.A., et al.: Automatic assessment of Alzheimer\u2019s across three languages using speech and language features. In: Proceedings of Interspeech, pp. 1748\u20131752. Dublin, Ireland (2023). https:\/\/doi.org\/10.21437\/Interspeech.2023-2079","DOI":"10.21437\/Interspeech.2023-2079"},{"key":"2_CR23","doi-asserted-by":"publisher","unstructured":"Schiel, F., Heinrich, C.: Laying the foundation for in-car alcohol detection by speech. In: Proceedings of Interspeech, pp. 983\u2013986. Brighton, United Kingdom (2009). https:\/\/doi.org\/10.21437\/Interspeech.2009-292","DOI":"10.21437\/Interspeech.2009-292"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Schneider, S., Baevski, A., Collobert, R., Auli, M.: wav2vec: unsupervised pre-training for speech recognition. In: Proceedings of Interspeech, pp. 3465\u20133469 (2019)","DOI":"10.21437\/Interspeech.2019-1873"},{"issue":"11","key":"2_CR25","doi-asserted-by":"publisher","first-page":"847","DOI":"10.1016\/j.biopsych.2017.04.019","volume":"82","author":"M Sebold","year":"2017","unstructured":"Sebold, M., et al.: When habits are dangerous: alcohol expectancies and habitual decision making predict relapse in alcohol dependence. Biol. Psychiat. 82(11), 847\u2013856 (2017)","journal-title":"Biol. Psychiat."},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Stavro1, K., Pelletier, J., Potvin, S.: Widespread and sustained cognitive deficits in alcoholism: a meta-analysis. Addict. Biol. 18, 203\u2013213 (2012)","DOI":"10.1111\/j.1369-1600.2011.00418.x"},{"issue":"3","key":"2_CR27","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1111\/1556-4029.15250","volume":"88","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. 88(3), 871\u2013883 (2023). https:\/\/doi.org\/10.1111\/1556-4029.15250","journal-title":"J. Forensic Sci."},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"T\u00f3th, L., et al.: Automatic detection of mild cognitive impairment from spontaneous speech using ASR. In: Proceedings of Interspeech, pp. 2694\u20132698. Dresden, Germany (2015)","DOI":"10.21437\/Interspeech.2015-568"},{"issue":"2","key":"2_CR29","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":"2_CR30","doi-asserted-by":"crossref","unstructured":"Vaessen, N., Van Leeuwen, D.A.: Fine-tuning wav2vec2 for speaker recognition. In: Proceedings of ICASSP, pp. 7967\u20137971 (2021)","DOI":"10.1109\/ICASSP43922.2022.9746952"},{"key":"2_CR31","doi-asserted-by":"publisher","unstructured":"Wagner, D., et al.: Multi-class detection of pathological speech with latent features: How does it perform on unseen data? In: Proceedings of Interspeech, pp. 2318\u20132322. Dublin, Ireland (2023). https:\/\/doi.org\/10.21437\/Interspeech.2023-464","DOI":"10.21437\/Interspeech.2023-464"},{"issue":"3","key":"2_CR32","doi-asserted-by":"publisher","first-page":"A293","DOI":"10.1121\/10.0018898","volume":"153","author":"R Wayland","year":"2023","unstructured":"Wayland, R., Tang, K., Wang, F., Vellozzi, S., Sengupta, R.: Neural networks\u2019 posterior probability as measure of effects of alcohol on speech. J. Acoust. Soc. Am. 153(3), A293 (2023). https:\/\/doi.org\/10.1121\/10.0018898","journal-title":"J. Acoust. Soc. Am."}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78014-1_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T15:06:19Z","timestamp":1736348779000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78014-1_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031780134","9783031780141"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78014-1_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 November 2024","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":"Belgrade","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Serbia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/specom2024.ftn.uns.ac.rs\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}