{"id":"https://openalex.org/W4392903765","doi":"https://doi.org/10.1109/icassp48485.2024.10446286","title":"Updated Corpora and Benchmarks for Long-Form Speech Recognition","display_name":"Updated Corpora and Benchmarks for Long-Form Speech Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903765","doi":"https://doi.org/10.1109/icassp48485.2024.10446286"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5058554117","display_name":"Jennifer Drexler Fox","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jennifer Drexler Fox","raw_affiliation_strings":["Rev.com"],"affiliations":[{"raw_affiliation_string":"Rev.com","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004777817","display_name":"Desh Raj","orcid":"https://orcid.org/0000-0002-5038-9400"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Desh Raj","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,USA","Center for Language and Speech Processing, Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090587898","display_name":"Natalie Delworth","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Natalie Delworth","raw_affiliation_strings":["Rev.com"],"affiliations":[{"raw_affiliation_string":"Rev.com","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092964180","display_name":"Quinn McNamara","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quinn McNamara","raw_affiliation_strings":["Rev.com"],"affiliations":[{"raw_affiliation_string":"Rev.com","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010857889","display_name":"Corey Miller","orcid":"https://orcid.org/0000-0003-2190-2583"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Corey Miller","raw_affiliation_strings":["Rev.com"],"affiliations":[{"raw_affiliation_string":"Rev.com","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037359921","display_name":"Mig\u00fcel Jett\u00e9","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mig\u00fcel Jett\u00e9","raw_affiliation_strings":["Rev.com"],"affiliations":[{"raw_affiliation_string":"Rev.com","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5058554117"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3379,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82550897,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"13246","last_page":"13250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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/T12031","display_name":"Speech and dialogue systems","score":0.9973000288009644,"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/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/computer-science","display_name":"Computer science","score":0.820469319820404},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7434322237968445},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7348788380622864},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6900047063827515},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.622817873954773},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5437374114990234},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5254979729652405},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5254846215248108},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5034438967704773},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4744466543197632},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4131561815738678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.820469319820404},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7434322237968445},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7348788380622864},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6900047063827515},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.622817873954773},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5437374114990234},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5254979729652405},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5254846215248108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5034438967704773},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4744466543197632},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4131561815738678},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2898130230","display_name":null,"funder_award_id":"120435","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5877145623","display_name":null,"funder_award_id":"2120435","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310145","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2125336414","https://openalex.org/W2127141656","https://openalex.org/W2526425061","https://openalex.org/W2799473636","https://openalex.org/W2886025712","https://openalex.org/W2891176389","https://openalex.org/W2936774411","https://openalex.org/W2937649809","https://openalex.org/W3007776460","https://openalex.org/W3008181812","https://openalex.org/W3008898571","https://openalex.org/W3015383801","https://openalex.org/W3093502359","https://openalex.org/W3096035558","https://openalex.org/W3096798607","https://openalex.org/W3097777922","https://openalex.org/W3101648800","https://openalex.org/W3119308075","https://openalex.org/W3149629662","https://openalex.org/W3161022068","https://openalex.org/W3197674197","https://openalex.org/W3198413388","https://openalex.org/W3198694222","https://openalex.org/W3200895333","https://openalex.org/W3208887030","https://openalex.org/W4224457787","https://openalex.org/W4283700324","https://openalex.org/W4283835659","https://openalex.org/W4286908472","https://openalex.org/W4360930497","https://openalex.org/W4372260432","https://openalex.org/W4372269772","https://openalex.org/W4378105483","https://openalex.org/W4385822425","https://openalex.org/W4385822648","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6638749077","https://openalex.org/W6678809451","https://openalex.org/W6684440257","https://openalex.org/W6784312278","https://openalex.org/W6840509714","https://openalex.org/W6847363464","https://openalex.org/W6852909395","https://openalex.org/W6855795314"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W2055243143","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177"],"abstract_inverted_index":{"The":[0],"vast":[1],"majority":[2],"of":[3],"ASR":[4,24,52,68],"research":[5],"uses":[6],"corpora":[7,74],"in":[8],"which":[9],"both":[10],"the":[11,77],"training":[12,102],"and":[13,39,56,60,83],"test":[14,27],"data":[15],"have":[16],"been":[17],"pre-segmented":[18],"into":[19],"utterances.":[20,44],"In":[21,45],"most":[22],"real-word":[23],"use-cases,":[25],"however,":[26],"audio":[28],"is":[29],"not":[30],"segmented,":[31],"leading":[32],"to":[33,62,75,93],"a":[34,99],"mismatch":[35,79],"between":[36],"inference-time":[37],"conditions":[38],"models":[40],"trained":[41],"on":[42],"segmented":[43],"this":[46,94,113],"paper,":[47],"we":[48,97],"re-release":[49],"three":[50],"standard":[51],"corpora\u2014TED-LIUM":[53],"3,":[54],"Gigapeech,":[55],"VoxPopulien\u2014with":[57],"updated":[58],"transcription":[59],"alignments":[61],"enable":[63],"their":[64],"use":[65,71],"for":[66,81,103,109],"long-form":[67,101],"research.":[69],"We":[70],"these":[72,104],"reconstituted":[73],"study":[76],"train-test":[78],"problem":[80],"transducers":[82],"attention-based":[84],"encoder-decoders":[85],"(AEDs),":[86],"confirming":[87],"that":[88],"AEDs":[89],"are":[90],"more":[91],"susceptible":[92],"issue.":[95],"Finally,":[96],"benchmark":[98],"simple":[100],"models,":[105],"showing":[106],"its":[107],"efficacy":[108],"model":[110],"robustness":[111],"under":[112],"domain":[114],"shift.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}