{"id":19848,"date":"2018-03-21T12:06:00","date_gmt":"2018-03-21T11:06:00","guid":{"rendered":"https:\/\/newsite.finki.ukim.mk\/events\/pokaneto-predavanje-od-d-r-aleksandru-nikolin\/"},"modified":"2026-06-12T09:50:31","modified_gmt":"2026-06-12T07:50:31","slug":"pokaneto-predavanje-od-d-r-aleksandru-nikolin","status":"publish","type":"event","link":"https:\/\/newsite.finki.ukim.mk\/en\/events\/pokaneto-predavanje-od-d-r-aleksandru-nikolin\/","title":{"rendered":"\u041f\u043e\u043a\u0430\u043d\u0435\u0442\u043e \u043f\u0440\u0435\u0434\u0430\u0432\u0430\u045a\u0435 \u043e\u0434 \u0434-\u0440 \u0410\u043b\u0435\u043a\u0441\u0430\u043d\u0434\u0440\u0443 \u041d\u0438\u043a\u043e\u043b\u0438\u043d"},"content":{"rendered":"<p>\u0424\u0418\u041d\u041a\u0418, \u0437\u0430\u0435\u0434\u043d\u043e \u0441\u043e \u043e\u0434\u0434\u0435\u043b\u043e\u0442 \u0437\u0430 \u043a\u043e\u043c\u043f\u0458\u0443\u0442\u0435\u0440\u0438 \u043f\u0440\u0438 \u043c\u0430\u043a\u0435\u0434\u043e\u043d\u0441\u043a\u0430\u0442\u0430 IEEE \u0441\u0435\u043a\u0446\u0438\u0458\u0430, \u043d\u0430 28.03.2018, \u0441\u043e \u043f\u043e\u0447\u0435\u0442\u043e\u043a \u0432\u043e 12:00 \u0447\u0430\u0441\u043e\u0442, \u0432\u043e \u0410\u041c\u0424 \u043d\u0430 \u0424\u0418\u041d\u041a\u0418 \u043e\u0440\u0433\u0430\u043d\u0438\u0437\u0438\u0440\u0430\u0430\u0442 \u043f\u043e\u043a\u0430\u043d\u0435\u0442\u043e \u043f\u0440\u0435\u0434\u0430\u0432\u0430\u045a\u0435 \u043d\u0430 \u0442\u0435\u043c\u0430: How to test a voice biometrics solution: statistics of the Romanian, Greek, and Macedonian languages.<\/p>\n<p>\u041f\u0440\u0435\u0434\u0430\u0432\u0430\u0447 \u045c\u0435 \u0431\u0438\u0434\u0435 \u0434-\u0440 \u0410\u043b\u0435\u043a\u0441\u0430\u043d\u0434\u0440\u0443 \u041d\u0438\u043a\u043e\u043b\u0438\u043d, \u0432\u043e\u043d\u0440\u0435\u0434\u0435\u043d \u043f\u0440\u043e\u0444\u0435\u0441\u043e\u0440 \u043d\u0430 \u0418\u043d\u0441\u0442\u0438\u0442\u0443\u0442\u043e\u0442 \u0437\u0430 \u0444\u0438\u0437\u0438\u043a\u0430 \u043f\u0440\u0438 \u0423\u043d\u0438\u0432\u0435\u0440\u0437\u0438\u0442\u0435\u0442\u043e\u0442 \u0432\u043e \u0411\u0443\u043a\u0443\u0440\u0435\u0448\u0442, \u0420\u043e\u043c\u0430\u043d\u0438\u0458\u0430.<\/p>\n<p>\u0410\u043f\u0441\u0442\u0440\u0430\u043a\u0442: Motivated by the development of a novel voice-biometrics solution within the H2020 SpeechXRays project, I will present a series of statistical results on the Romanian, Greek, and Macedonian languages that can be used to check the accuracy of voice biometrics solutions across the phonetic spectrum of the aforementioned languages. We revisit the concept of phonetic balance and argue that in addition to the correct distribution of phonems a good set of test utterances should also have the correct distribution of clusters of phonems and should account for familiarity and comfort of the users with the individual words within the test utterances.<\/p>","protected":false},"featured_media":19849,"template":"","tags":[],"class_list":["post-19848","event","type-event","status-publish","has-post-thumbnail","hentry"],"_links":{"self":[{"href":"https:\/\/newsite.finki.ukim.mk\/en\/wp-json\/wp\/v2\/event\/19848","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/newsite.finki.ukim.mk\/en\/wp-json\/wp\/v2\/event"}],"about":[{"href":"https:\/\/newsite.finki.ukim.mk\/en\/wp-json\/wp\/v2\/types\/event"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/newsite.finki.ukim.mk\/en\/wp-json\/wp\/v2\/media\/19849"}],"wp:attachment":[{"href":"https:\/\/newsite.finki.ukim.mk\/en\/wp-json\/wp\/v2\/media?parent=19848"}],"wp:term":[{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/newsite.finki.ukim.mk\/en\/wp-json\/wp\/v2\/tags?post=19848"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}