{"id":"https://openalex.org/W7148240812","doi":"https://doi.org/10.1109/asru65441.2025.11434751","title":"Whispering Context: Distilling Syntax and Semantics for Long Speech Transcripts","display_name":"Whispering Context: Distilling Syntax and Semantics for Long Speech Transcripts","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148240812","doi":"https://doi.org/10.1109/asru65441.2025.11434751"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132807448","display_name":"Duygu Altinok","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164339","display_name":"Oldham Council","ror":"https://ror.org/05cxzzq07","country_code":"GB","type":"government","lineage":["https://openalex.org/I4210164339"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Duygu Altinok","raw_affiliation_strings":["Independent Researcher,Berlin,Germany"],"affiliations":[{"raw_affiliation_string":"Independent Researcher,Berlin,Germany","institution_ids":["https://openalex.org/I4210164339"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5132807448"],"corresponding_institution_ids":["https://openalex.org/I4210164339"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87545625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5123999714851379,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5123999714851379,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.26510000228881836,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.09279999881982803,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.6751000285148621},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6036999821662903},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5993000268936157},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5412999987602234},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48339998722076416},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4731999933719635},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.4648999869823456},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4350999891757965}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8220999836921692},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.6751000285148621},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6536999940872192},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6036999821662903},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5993000268936157},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5412999987602234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.524399995803833},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48339998722076416},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4731999933719635},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4650000035762787},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.4648999869823456},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4350999891757965},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.258899986743927}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2003447360","https://openalex.org/W2034190452","https://openalex.org/W2106851243","https://openalex.org/W2782717521","https://openalex.org/W3034368386","https://openalex.org/W3095918555","https://openalex.org/W4233762729","https://openalex.org/W4385822287","https://openalex.org/W4406461754"],"related_works":[],"abstract_inverted_index":{"ASR":[0,31,125],"systems":[1],"often":[2],"struggle":[3],"with":[4,49,81],"maintaining":[5],"syntactic":[6],"and":[7,22,55,58,68,72,84,96,104],"semantic":[8],"accuracy":[9],"in":[10,89,126],"long":[11,82],"audio":[12],"transcripts,":[13],"impacting":[14],"tasks":[15],"like":[16],"Named":[17],"Entity":[18],"Recognition":[19],"(NER),":[20],"capitalization,":[21,95],"punctuation.":[23],"We":[24],"propose":[25],"a":[26,120],"novel":[27,101],"approach":[28],"that":[29],"enhances":[30],"by":[32],"distilling":[33],"contextual":[34],"knowledge":[35],"from":[36],"LLaMA":[37],"models":[38],"into":[39,117],"Whisper.":[40],"Our":[41],"method":[42],"uses":[43],"two":[44],"strategies:":[45],"(1)":[46],"token-level":[47],"distillation":[48],"optimal":[50],"transport":[51],"to":[52],"align":[53],"dimensions":[54],"sequence":[56],"lengths,":[57],"(2)":[59],"representation":[60],"loss":[61],"minimization":[62],"between":[63],"sentence":[64],"embeddings":[65],"of":[66,113],"Whisper":[67],"LLaMA,":[69],"blending":[70],"syntax":[71],"semantics.":[73],"Evaluations":[74],"on":[75],"the":[76,111],"Spoken":[77],"Wikipedia":[78],"dataset\u2014a":[79],"benchmark":[80],"audios":[83],"rich":[85],"entities\u2014demonstrate":[86],"significant":[87],"improvements":[88],"Word":[90],"Error":[91],"Rate":[92],"(WER),":[93],"NER,":[94],"punctuation":[97],"success.":[98],"By":[99],"introducing":[100],"NER":[102],"metrics":[103],"exploring":[105],"semantics-aware":[106],"ASR,":[107],"our":[108],"work":[109],"highlights":[110],"value":[112],"integrating":[114],"linguistic":[115],"context":[116],"transcription,":[118],"setting":[119],"foundation":[121],"for":[122],"robust,":[123],"context-aware":[124],"long-form":[127],"speech.":[128]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}