{"id":{"repo_id":"brno-tech","oai_identifier":"oai:dspace.vut.cz:11012/180586"},"canonical_url":"https://search.dev.ndltd.org/etd/brno-tech/oai:dspace.vut.cz:11012/180586","repository":{"repo_id":"brno-tech","name":"Brno University of Technology","base_url":"https://dspace.vut.cz/oai/request"},"display":{"title":"Topic Identification from Spoken TED-Talks","abstract":"Táto práca sa zaoberá problémom spracovania prirodzeného jazyka a následnej klasifikácie. Použité systémy boli modelované na TED-LIUM korpuse. Systém automatického spracovania jazyka bol modelovaný s použitím sady nástrojov Kaldi. Vo výsledku bol dosiahnutý WER s hodnotou 16.6\\%. Problém klasifikácie textu bol adresovaný s pomocou metód na lineárnu klasifikáciu, konkrétne Multinomial Naive Bayes a Linear Support Vector Machines, kde druhá technika dosiahla vyššiu presnosť klasifikácie.","abstract_html":"Táto práca sa zaoberá problémom spracovania prirodzeného jazyka a následnej klasifikácie. Použité systémy boli modelované na TED-LIUM korpuse. Systém automatického spracovania jazyka bol modelovaný s použitím sady nástrojov Kaldi. Vo výsledku bol dosiahnutý WER s hodnotou 16.6\\%. Problém klasifikácie textu bol adresovaný s pomocou metód na lineárnu klasifikáciu, konkrétne Multinomial Naive Bayes a Linear Support Vector Machines, kde druhá technika dosiahla vyššiu presnosť klasifikácie.","abstract_has_math":false,"creators":["Vašš, Adam"],"institution":"Vysoké učení technické v Brně. Fakulta informačních technologií","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Kesiraju, Santosh"],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-07-24T01:22:53Z","subjects":["TED","talks","identifikácia tém","strojové učenie","klasifikácia","transkripcia","lineárna klasifikácia","Kaldi","support vector machines","akustický model","lingvistický model","TED-LIUM","ASR","topic identification","machine learning","classification","transcription","linear classification","acoustic modeling","language modeling"],"languages":["en"],"rights":["Standardní licenční smlouva - přístup k plnému textu bez omezení"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["121941"],"render_values":[{"text":"121941","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/11012/180586","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Kesiraju, Santosh"]},{"key":"dc:creator","label":"Author","values":["Vašš, Adam"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:publisher","label":"Institution","values":["Vysoké učení technické v Brně. Fakulta informačních technologií"]},{"key":"dc:type","label":"Dc Type","values":["Text"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Bc."]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["TED","talks","identifikácia tém","strojové učenie","klasifikácia","transkripcia","lineárna klasifikácia","Kaldi","support vector machines","akustický model","lingvistický model","TED-LIUM","ASR","topic identification","machine learning","classification","transcription","linear classification","acoustic modeling","language modeling"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Standardní licenční smlouva - přístup k plnému textu bez omezení"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["121941"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/11012/180586"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Táto práca sa zaoberá problémom spracovania prirodzeného jazyka a následnej klasifikácie. Použité systémy boli modelované na TED-LIUM korpuse. Systém automatického spracovania jazyka bol modelovaný s použitím sady nástrojov Kaldi. Vo výsledku bol dosiahnutý WER s hodnotou 16.6\\%. Problém klasifikácie textu bol adresovaný s pomocou metód na lineárnu klasifikáciu, konkrétne Multinomial Naive Bayes a Linear Support Vector Machines, kde druhá technika dosiahla vyššiu presnosť klasifikácie.","This thesis deals with the problems of language recognition and topic classification, using TED-LIUM corpus to train both the ASR and classification models. The ASR system is built using the Kaldi toolkit, achieving the WER of 16.6\\%. The classification problem is addressed using linear classification methods, specifically Multinomial Naive Bayes and Linear Support Vector Machines, the latter method achieving higher topic classification accuracy."]},{"key":"dc:title","label":"Title","values":["Topic Identification from Spoken TED-Talks"]}]}],"canonical_facts":{"dc:contributor.advisor":["Kesiraju, Santosh"],"dc:creator":["Vašš, Adam"],"dc:description.abstract":["Táto práca sa zaoberá problémom spracovania prirodzeného jazyka a následnej klasifikácie. Použité systémy boli modelované na TED-LIUM korpuse. Systém automatického spracovania jazyka bol modelovaný s použitím sady nástrojov Kaldi. Vo výsledku bol dosiahnutý WER s hodnotou 16.6\\%. Problém klasifikácie textu bol adresovaný s pomocou metód na lineárnu klasifikáciu, konkrétne Multinomial Naive Bayes a Linear Support Vector Machines, kde druhá technika dosiahla vyššiu presnosť klasifikácie.","This thesis deals with the problems of language recognition and topic classification, using TED-LIUM corpus to train both the ASR and classification models. The ASR system is built using the Kaldi toolkit, achieving the WER of 16.6\\%. The classification problem is addressed using linear classification methods, specifically Multinomial Naive Bayes and Linear Support Vector Machines, the latter method achieving higher topic classification accuracy."],"dc:identifier.other":["121941"],"dc:identifier.uri":["http://hdl.handle.net/11012/180586"],"dc:language.iso":["en"],"dc:publisher":["Vysoké učení technické v Brně. Fakulta informačních technologií"],"dc:rights":["Standardní licenční smlouva - přístup k plnému textu bez omezení"],"dc:subject":["TED","talks","identifikácia tém","strojové učenie","klasifikácia","transkripcia","lineárna klasifikácia","Kaldi","support vector machines","akustický model","lingvistický model","TED-LIUM","ASR","topic identification","machine learning","classification","transcription","linear classification","acoustic modeling","language modeling"],"dc:title":["Topic Identification from Spoken TED-Talks"],"dc:type":["Text"],"thesis:institution_name":["Bc."]},"updated_at":"2026-07-24T01:22:53Z"}