{"id":{"repo_id":"vilnius","oai_identifier":"oai:vu.lt:elaba:308334924"},"canonical_url":"https://search.ndltd.org/etd/vilnius/oai:vu.lt:elaba:308334924","repository":{"repo_id":"vilnius","name":"Vilnius University","base_url":"https://epublications.vu.lt/oai"},"display":{"title":"Triukšmui atsparus AM radijo kalbos atpažinimo modelis su maršrutizavimu sąlygotais LoRA adapteriais /","abstract":"This work presents a hybrid system for automatic speech recognition (ASR) in aviation very high frequency (VHF) radio communications. A novel methodology is introduced, combining an ECAPA-TDNN classification model used as an audio routing component with four distinct Whisper-Small LoRA adapters, each conditioned on specific noise pseudo-labels. This architecture allows even a relatively small model to achieve competitive transcription accuracy. Compared to the baseline Whisper-Small, Whisper-Large models, and a non-conditional LoRA adapter, the proposed system achieved word error rate (WER) reductions of 77~\\%, 66.65~\\%, and 5.76~\\% respectively. Compared to existing specialized models, the proposed system trails by only 9.78~\\% points while being 6.4 times smaller. Additionally, a methodology for synthesizing VHF amplitude modulation (VHF AM) radio data using open-source tools was developed.","abstract_html":"This work presents a hybrid system for automatic speech recognition (ASR) in aviation very high frequency (VHF) radio communications. A novel methodology is introduced, combining an ECAPA-TDNN classification model used as an audio routing component with four distinct Whisper-Small LoRA adapters, each conditioned on specific noise pseudo-labels. This architecture allows even a relatively small model to achieve competitive transcription accuracy. Compared to the baseline Whisper-Small, Whisper-Large models, and a non-conditional LoRA adapter, the proposed system achieved word error rate (WER) reductions of 77~\\%, 66.65~\\%, and 5.76~\\% respectively. Compared to existing specialized models, the proposed system trails by only 9.78~\\% points while being 6.4 times smaller. Additionally, a methodology for synthesizing VHF amplitude modulation (VHF AM) radio data using open-source tools was developed.","abstract_has_math":false,"creators":["Sabaitis, Rokas,"],"institution":"Institutional Repository of Vilnius University","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-19T10:12:55Z","subjects":[],"languages":["lit"],"rights":["info:eu-repo/semantics/openAccess"],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://repository.vu.lt/VU:ELABAETD308334924&prefLang=en_US","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://repository.vu.lt/VU:ELABAETD308334924&prefLang=en_US","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":"open","embargo_until":null,"access_note":null},"source_record":{"url":"https://epublications.vu.lt/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Avu.lt%3Aelaba%3A308334924","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Sabaitis, Rokas,"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026"]},{"key":"dc:publisher","label":"Institution","values":["Institutional Repository of Vilnius University"]},{"key":"dc:relation","label":"Dc Relation","values":["https://epublications.vu.lt/object/elaba:308334924/308334924.pdf"]},{"key":"dc:type","label":"Dc Type","values":["info:eu-repo/semantics/bachelorThesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["lit"]},{"key":"dc:rights","label":"Dc Rights","values":["info:eu-repo/semantics/openAccess"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://repository.vu.lt/VU:ELABAETD308334924&prefLang=en_US"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["This work presents a hybrid system for automatic speech recognition (ASR) in aviation very high frequency (VHF) radio communications. A novel methodology is introduced, combining an ECAPA-TDNN classification model used as an audio routing component with four distinct Whisper-Small LoRA adapters, each conditioned on specific noise pseudo-labels. This architecture allows even a relatively small model to achieve competitive transcription accuracy. Compared to the baseline Whisper-Small, Whisper-Large models, and a non-conditional LoRA adapter, the proposed system achieved word error rate (WER) reductions of 77~\\%, 66.65~\\%, and 5.76~\\% respectively. Compared to existing specialized models, the proposed system trails by only 9.78~\\% points while being 6.4 times smaller. Additionally, a methodology for synthesizing VHF amplitude modulation (VHF AM) radio data using open-source tools was developed."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Triukšmui atsparus AM radijo kalbos atpažinimo modelis su maršrutizavimu sąlygotais LoRA adapteriais /","A noise-robust speech recognition model for am radio with routing-conditioned lora adapters."]}]}],"canonical_facts":{"dc:creator":["Sabaitis, Rokas,"],"dc:date":["2026"],"dc:description":["This work presents a hybrid system for automatic speech recognition (ASR) in aviation very high frequency (VHF) radio communications. A novel methodology is introduced, combining an ECAPA-TDNN classification model used as an audio routing component with four distinct Whisper-Small LoRA adapters, each conditioned on specific noise pseudo-labels. This architecture allows even a relatively small model to achieve competitive transcription accuracy. Compared to the baseline Whisper-Small, Whisper-Large models, and a non-conditional LoRA adapter, the proposed system achieved word error rate (WER) reductions of 77~\\%, 66.65~\\%, and 5.76~\\% respectively. Compared to existing specialized models, the proposed system trails by only 9.78~\\% points while being 6.4 times smaller. Additionally, a methodology for synthesizing VHF amplitude modulation (VHF AM) radio data using open-source tools was developed."],"dc:format":["application/pdf"],"dc:identifier":["https://repository.vu.lt/VU:ELABAETD308334924&prefLang=en_US"],"dc:language":["lit"],"dc:publisher":["Institutional Repository of Vilnius University"],"dc:relation":["https://epublications.vu.lt/object/elaba:308334924/308334924.pdf"],"dc:rights":["info:eu-repo/semantics/openAccess"],"dc:title":["Triukšmui atsparus AM radijo kalbos atpažinimo modelis su maršrutizavimu sąlygotais LoRA adapteriais /","A noise-robust speech recognition model for am radio with routing-conditioned lora adapters."],"dc:type":["info:eu-repo/semantics/bachelorThesis"]},"updated_at":"2026-11-19T10:12:55Z"}