{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T15:01:49Z","timestamp":1781881309327,"version":"3.54.5"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031134470","type":"print"},{"value":"9783031134487","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\/978-3-031-13448-7_9","type":"book-chapter","created":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T23:03:22Z","timestamp":1661209402000},"page":"108-118","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Identification of\u00a0Subjects Wearing a\u00a0Surgical Mask from\u00a0Their Speech by\u00a0Means of\u00a0X-vectors and\u00a0Fisher Vectors"],"prefix":"10.1007","author":[{"given":"Jos\u00e9 Vicente","family":"Egas-L\u00f3pez","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G\u00e1bor","family":"Gosztolya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,8,23]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Egas-L\u00f3pez, J.V., Orozco-Arroyave, J.R., Gosztolya, G.: Assessing Parkinson\u2019s disease from speech using fisher vectors. In: Proceedings of Interspeech (2019)","DOI":"10.21437\/Interspeech.2019-2217"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Gosztolya, G., Bagi, A., Szal\u00f3ki, S., Szendi, I., Hoffmann, I.: Identifying schizophrenia based on temporal parameters in spontaneous speech. In: Proceedings of Interspeech, Hyderabad, India, pp. 3408\u20133412, September 2018","DOI":"10.21437\/Interspeech.2018-1079"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Gr\u00f3sz, T., Busa-Fekete, R., Gosztolya, G., T\u00f3th, L.: Assessing the degree of nativeness and Parkinson\u2019s condition using Gaussian processes and deep rectifier neural networks. In: Proceedings of Interspeech, Dresden, Germany, pp. 1339\u20131343, September 2015","DOI":"10.21437\/Interspeech.2015-195"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Gosztolya, G., Gr\u00f3sz, T., T\u00f3th, L.: General utterance-level feature extraction for classifying crying sounds, atypical & self-assessed affect and heart beats. In: Proceedings of Interspeech, Hyderabad, India, pp. 531\u2013535, September 2018","DOI":"10.21437\/Interspeech.2018-1076"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Gosztolya, G., Gr\u00f3sz, T., Szasz\u00e1k, G., T\u00f3th, L.: Estimating the sincerity of apologies in speech by DNN rank learning and prosodic analysis. In: Proceedings of Interspeech, San Francisco, CA, USA, pp. 2026\u20132030, September 2016","DOI":"10.21437\/Interspeech.2016-956"},{"issue":"9\u201310","key":"9_CR6","doi-asserted-by":"publisher","first-page":"1062","DOI":"10.1016\/j.specom.2011.01.011","volume":"53","author":"B Schuller","year":"2011","unstructured":"Schuller, B., Batliner, A., Steidl, S., Seppi, D.: Recognising realistic emotions and affect in speech: state of the art and lessons learnt from the first challenge. Speech Commun. 53(9\u201310), 1062\u20131087 (2011)","journal-title":"Speech Commun."},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Schuller, B.W., et al.: The INTERSPEECH 2020 computational paralinguistics challenge: elderly emotion, breathing & masks. In: Proceedings of Interspeech, Shanghai, China, p. 5, September 2020","DOI":"10.21437\/Interspeech.2020-32"},{"issue":"4","key":"9_CR8","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2011","unstructured":"Dehak, N., Kenny, P.J., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19(4), 788\u2013798 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"9_CR9","doi-asserted-by":"publisher","first-page":"1534","DOI":"10.1016\/j.procs.2018.08.126","volume":"126","author":"NS Ibrahim","year":"2018","unstructured":"Ibrahim, N.S., Ramli, D.A.: I-vector extraction for speaker recognition based on dimensionality reduction. Procedia Comput. Sci. 126, 1534\u20131540 (2018)","journal-title":"Procedia Comput. Sci."},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Garcia-Romero, D., Espy-Wilson, C.Y.: Analysis of i-vector length normalization in speaker recognition systems. In: Twelfth Annual Conference of the International Speech Communication Association (2011)","DOI":"10.21437\/Interspeech.2011-53"},{"key":"9_CR11","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/978-3-030-26061-3_30","volume-title":"Speech and Computer","author":"JV Egas L\u00f3pez","year":"2019","unstructured":"Egas L\u00f3pez, J.V., T\u00f3th, L., Hoffmann, I., K\u00e1lm\u00e1n, J., P\u00e1k\u00e1ski, M., Gosztolya, G.: Assessing Alzheimer\u2019s disease from speech using the i-vector approach. In: Salah, A.A., Karpov, A., Potapova, R. (eds.) SPECOM 2019. LNCS (LNAI), vol. 11658, pp. 289\u2013298. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-26061-3_30"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Cummins, N., Epps, J., Sethu, V., Krajewski, J.: Variability compensation in small data: oversampled extraction of i-vectors for the classification of depressed speech. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 970\u2013974 (2014)","DOI":"10.1109\/ICASSP.2014.6853741"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., Khudanpur, S.: X-vectors: robust DNN embeddings for speaker verification. In: Proceedings of ICASSP, pp. 5329\u20135333 (2018)","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Silnova, A., Brummer, N., Garcia-Romero, D., Snyder, D., Burget, L.: Fast variational bayes for heavy-tailed PLDA applied to i-vectors and x-vectors. arXiv preprint: arXiv:1803.09153 (2018)","DOI":"10.21437\/Interspeech.2018-2128"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., McCree, A., Povey, D., Khudanpur, S.: Speaker recognition for multi-speaker conversations using x-vectors. In: Proceedings of ICASSP (2019)","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Nagrani, A., Zisserman, A.: VoxCeleb2: Deep Speaker Recognition. arXiv preprint arXiv:1806.05622 (2018)","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Novotn\u1ef3, O., Plchot, O., Matejka, P., Mosner, L., Glembek, O.: On the use of x-vectors for robust speaker recognition. In: Proceedings of Odyssey, pp. 168\u2013175 (2018)","DOI":"10.21437\/Odyssey.2018-24"},{"key":"9_CR18","unstructured":"Zargarbashi, S., Babaali, B.: A multi-modal feature embedding approach to diagnose Alzheimer\u2019s disease from spoken language. arXiv preprint arXiv:1910.00330 (2019)"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Pappagari, R., Wang, T., Villalba, J., Chen, N., Dehak, N.: X-vectors meet emotions: a study on dependencies between emotion and speaker verification. In: Proceedings of ICASSP, pp. 7169\u20137173 (2020)","DOI":"10.1109\/ICASSP40776.2020.9054317"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Raj, D., Snyder, D., Povey, D., Khudanpur, S.: Probing the information encoded in x-vectors. arXiv preprint arXiv:1909.06351 (2019)","DOI":"10.1109\/ASRU46091.2019.9003979"},{"key":"9_CR21","unstructured":"Jaakkola, T.S., Haussler, D.: Exploiting generative models in discriminative classifiers. In: Proceedings of NIPS, Denver, CO, USA, pp. 487\u2013493 (1998)"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Song, Y., Zou, J.J., Chang, H., Cai, W.: Adapting Fisher vectors for histopathology image classification. In: Proceedings of ISBI, pp. 600\u2013603. IEEE (2017)","DOI":"10.1109\/ISBI.2017.7950592"},{"key":"9_CR23","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1007\/978-3-319-99579-3_21","volume-title":"Speech and Computer","author":"F Hernandez","year":"2018","unstructured":"Hernandez, F., Nguyen, V., Ghannay, S., Tomashenko, N., Est\u00e8ve, Y.: TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation. In: Karpov, A., Jokisch, O., Potapova, R. (eds.) SPECOM 2018. LNCS (LNAI), vol. 11096, pp. 198\u2013208. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-99579-3_21"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Povey, D., Khudanpur, S.: Deep neural network embeddings for text-independent speaker verification. In: Proceedings of Interspeech (2017)","DOI":"10.21437\/Interspeech.2017-620"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Snyder, D., Ghahremani, P., Povey, D., Garcia-Romero, D., Carmiel, Y., Khudanpur, S.: Deep neural network-based speaker embeddings for end-to-end speaker verification. In: Proceedings of SLT, pp. 165\u2013170 (2016)","DOI":"10.1109\/SLT.2016.7846260"},{"key":"9_CR26","unstructured":"Povey, D., et al.: The Kaldi speech recognition toolkit. In: Proceedings of ASRU (2011)"},{"issue":"2","key":"9_CR27","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60(2), 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vision"},{"key":"9_CR28","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.cviu.2016.03.013","volume":"150","author":"X Peng","year":"2016","unstructured":"Peng, X., Wang, L., Wang, X., Qiao, Y.: Bag of Visual Words and fusion methods for action recognition: comprehensive study and good practice. Comput. Vis. Image Underst. 150, 109\u2013125 (2016)","journal-title":"Comput. Vis. Image Underst."},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Moreno, P.J., Rifkin, R.: Using the Fisher kernel method for web audio classification. In: Proceedings of ICASSP, Dallas, TX, USA, pp. 2417\u20132420 (2010)","DOI":"10.1109\/ICASSP.2000.859329"},{"key":"9_CR30","doi-asserted-by":"crossref","unstructured":"Tian, Y., He, L., Li, Z.Y., Wu, W.L., Zhang, W.Q., Liu, J.: Speaker verification using Fisher vector. In: Proceedings of ISCSLP, Singapore, Singapore, pp. 419\u2013422 (2014)","DOI":"10.1109\/ISCSLP.2014.6936620"},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Zaj\u00edc, Z., Hr\u00faz, M.: Fisher vectors in PLDA speaker verification system. In: Proceedings of ICSP, Chengdu, China, pp. 1338\u20131341 (2016)","DOI":"10.1109\/ICSP.2016.7878044"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Kaya, H., Karpov, A.A., Salah, A.A.: Fisher vectors with cascaded normalization for paralinguistic analysis. In: Proceedings of Interspeech, pp. 909\u2013913 (2015)","DOI":"10.21437\/Interspeech.2015-193"},{"key":"9_CR33","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1007\/s11263-013-0636-x","volume":"105","author":"J S\u00e1nchez","year":"2013","unstructured":"S\u00e1nchez, J., Perronnin, F., Mensink, T., Verbeek, J.: Image classification with the fisher vector: theory and practice. Int. J. Comput. Vision 105, 222\u2013245 (2013)","journal-title":"Int. J. Comput. Vision"},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Dance, C.: Fisher kernels on visual vocabularies for image categorization. In: Proceedings of CVPR (2007)","DOI":"10.1109\/CVPR.2007.383266"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Smith, D.C., Kornelson, K.A.: A comparison of Fisher vectors and Gaussian supervectors for document versus non-document image classification. In: Applications of Digital Image Processing XXXVI, vol. 8856, p. 88560N. International Society for Optics and Photonics (2013)","DOI":"10.1117\/12.2023329"},{"key":"9_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"C-C Chang","year":"2011","unstructured":"Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 1\u201327 (2011)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"Vedaldi, A., Fulkerson, B.: VLFeat: an open and portable library of computer vision algorithms. In: Proceedings of ACM Multimedia, pp. 1469\u20131472 (2010)","DOI":"10.1145\/1873951.1874249"}],"container-title":["Lecture Notes in Computer Science","Modeling Decisions for Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-13448-7_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T08:32:31Z","timestamp":1727857951000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-13448-7_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031134470","9783031134487"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-13448-7_9","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":"23 August 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MDAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Modeling Decisions for Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sant Cugat","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","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":"30 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mdai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/mdai.cat\/mdai2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"None","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"41","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"16","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"39% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}