{"id":"https://openalex.org/W7148389373","doi":"https://doi.org/10.1109/asru65441.2025.11434797","title":"WhisperNER: Unified Open Named Entity and Speech Recognition","display_name":"WhisperNER: Unified Open Named Entity and Speech Recognition","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148389373","doi":"https://doi.org/10.1109/asru65441.2025.11434797"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434797","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/A5114369217","display_name":"Gil Ayache","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gil Ayache","raw_affiliation_strings":["aiOla Research"],"affiliations":[{"raw_affiliation_string":"aiOla Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074687833","display_name":"Menachem Pirchi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Menachem Pirchi","raw_affiliation_strings":["Independent Researcher"],"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076537607","display_name":"Aviv Navon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aviv Navon","raw_affiliation_strings":["aiOla Research"],"affiliations":[{"raw_affiliation_string":"aiOla Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040863261","display_name":"Aviv Shamsian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aviv Shamsian","raw_affiliation_strings":["aiOla Research"],"affiliations":[{"raw_affiliation_string":"aiOla Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072070363","display_name":"Gill Hetz","orcid":"https://orcid.org/0000-0002-6477-7797"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gill Hetz","raw_affiliation_strings":["aiOla Research"],"affiliations":[{"raw_affiliation_string":"aiOla Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008847407","display_name":"Joseph Keshet","orcid":"https://orcid.org/0000-0003-2332-5783"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Joseph Keshet","raw_affiliation_strings":["aiOla Research and Technion"],"affiliations":[{"raw_affiliation_string":"aiOla Research and Technion","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5114369217"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87560853,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7645000219345093,"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":0.7645000219345093,"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":0.11400000005960464,"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":0.02419999986886978,"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/named-entity-recognition","display_name":"Named-entity recognition","score":0.8507000207901001},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6783000230789185},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6365000009536743},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.6183000206947327},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.44519999623298645},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.328900009393692},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3098999857902527}],"concepts":[{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.8507000207901001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.820900022983551},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6783000230789185},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.671999990940094},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.650600016117096},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6365000009536743},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.6183000206947327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5564000010490417},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.44519999623298645},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C2984865316","wikidata":"https://www.wikidata.org/wiki/Q25481968","display_name":"Speech act","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434797","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2035807240","https://openalex.org/W2087079002","https://openalex.org/W3100460087","https://openalex.org/W3119308075","https://openalex.org/W4226103796","https://openalex.org/W4285209801","https://openalex.org/W4319862635","https://openalex.org/W4361199948","https://openalex.org/W4372268584","https://openalex.org/W4382202688","https://openalex.org/W4385571440","https://openalex.org/W4389518714","https://openalex.org/W4389520763","https://openalex.org/W4391021545","https://openalex.org/W4391021753","https://openalex.org/W4401042470","https://openalex.org/W4401043472","https://openalex.org/W4401044087","https://openalex.org/W4402112196","https://openalex.org/W4402112556","https://openalex.org/W4402670463","https://openalex.org/W4402684123","https://openalex.org/W4411120260"],"related_works":[],"abstract_inverted_index":{"Integrating":[0],"named":[1],"entity":[2,31],"recognition":[3,8,38],"(NER)":[4],"with":[5,58,72,82,113],"automatic":[6],"speech":[7,28,60,102],"(ASR)":[9],"can":[10],"significantly":[11],"enhance":[12],"transcription":[13,29],"accuracy":[14],"and":[15,30,85,108,130],"enrich":[16],"its":[17],"content.":[18],"We":[19],"introduce":[20],"WhisperNER,":[21],"a":[22,54],"novel":[23],"model":[24,79],"that":[25,120],"facilitates":[26],"joint":[27],"recognition.":[32],"WhisperNER":[33,68,121],"supports":[34],"opentype":[35],"NER,":[36],"enabling":[37],"of":[39],"various":[40,73],"entities":[41],"during":[42],"inference.":[43],"Building":[44],"on":[45,69],"recent":[46],"advancements":[47],"in":[48,125],"open":[49,114],"NER":[50,74,83,106,115,129],"research,":[51],"we":[52,99],"augment":[53],"large":[55],"synthetic":[56,59,101],"dataset":[57],"samples.":[61],"This":[62],"approach":[63],"enables":[64],"us":[65],"to":[66,87],"train":[67],"numerous":[70],"examples":[71],"tags.":[75,116],"During":[76],"training,":[77],"the":[78,89,93],"is":[80],"prompted":[81],"labels":[84],"optimized":[86],"produce":[88],"transcribed":[90],"utterance":[91],"alongside":[92],"corresponding":[94],"tagged":[95],"entities.":[96],"For":[97],"evaluation,":[98],"generate":[100],"for":[103],"commonly":[104],"used":[105],"benchmarks":[107],"annotate":[109],"existing":[110],"ASR":[111],"datasets":[112],"Our":[117],"experiments":[118],"show":[119],"outperforms":[122],"natural":[123],"baselines":[124],"both":[126],"out-of-domain":[127],"open-type":[128],"supervised":[131],"fine-tuning.":[132]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}
