{"id":"https://openalex.org/W4392909067","doi":"https://doi.org/10.1109/icassp48485.2024.10448309","title":"Investigating End-to-End ASR Architectures for Long Form Audio Transcription","display_name":"Investigating End-to-End ASR Architectures for Long Form Audio Transcription","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909067","doi":"https://doi.org/10.1109/icassp48485.2024.10448309"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448309","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":"conference-paper","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/A5040007143","display_name":"Nithin Rao Koluguri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nithin Rao Koluguri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039963047","display_name":"Samuel Kriman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Kriman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092905726","display_name":"Georgy Zelenfroind","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georgy Zelenfroind","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027823948","display_name":"Somshubra Majumdar","orcid":"https://orcid.org/0000-0001-5635-4893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Somshubra Majumdar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091932262","display_name":"Dima Rekesh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dima Rekesh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005843015","display_name":"Vahid Noroozi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vahid Noroozi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040747392","display_name":"Jagadeesh Balam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jagadeesh Balam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13366","last_page":"13370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.8211707472801208},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.717812716960907},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5528832077980042},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5498412847518921},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4901328980922699},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.47195425629615784},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.41052916646003723},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3764350712299347},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.2592598795890808},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09822219610214233}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8211707472801208},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.717812716960907},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5528832077980042},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5498412847518921},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4901328980922699},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.47195425629615784},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.41052916646003723},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3764350712299347},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2592598795890808},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09822219610214233},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448309","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W2520160253","https://openalex.org/W2799473636","https://openalex.org/W2963414781","https://openalex.org/W2973215447","https://openalex.org/W3008181812","https://openalex.org/W3008898571","https://openalex.org/W3015537910","https://openalex.org/W3095173472","https://openalex.org/W3097777922","https://openalex.org/W3101648800","https://openalex.org/W3125815078","https://openalex.org/W3141854550","https://openalex.org/W3160766462","https://openalex.org/W3197478142","https://openalex.org/W3197674197","https://openalex.org/W4224457787","https://openalex.org/W4240984273","https://openalex.org/W4311000453","https://openalex.org/W4320930577","https://openalex.org/W4372349408","https://openalex.org/W4391021542","https://openalex.org/W6638749077","https://openalex.org/W6727336983","https://openalex.org/W6746023985","https://openalex.org/W6790121257","https://openalex.org/W6792376965","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W2610189143","https://openalex.org/W2159424856","https://openalex.org/W200981350","https://openalex.org/W4386907265","https://openalex.org/W2058752985","https://openalex.org/W2293740626","https://openalex.org/W1499712254","https://openalex.org/W2915347927"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"overview":[4],"and":[5,37,51,60,74,77,89,106,109,117],"evaluation":[6],"of":[7,9,21,69,84],"some":[8],"the":[10,53,82,93],"end-to-end":[11],"ASR":[12,46],"models":[13,25,40,103,113],"on":[14,27,66,121],"long-form":[15],"audio.":[16,124],"We":[17,43,100],"study":[18],"three":[19],"categories":[20],"Automatic":[22],"Speech":[23],"Recognition(ASR)":[24],"based":[26],"their":[28],"core":[29],"architecture:":[30],"(1)":[31],"convolutional,":[32],"(2)":[33],"convolutional":[34,39],"with":[35,41,86,104],"squeeze-and-excitation,":[36],"(3)":[38],"attention.":[42],"selected":[44],"one":[45],"model":[47,65,80],"from":[48,81],"each":[49,64],"category":[50,83],"evaluated":[52],"Word":[54],"Error":[55],"Rate,":[56],"maximum":[57],"audio":[58,71],"length":[59],"real-time":[61],"factor":[62],"for":[63],"a":[67],"variety":[68],"long":[70,122],"benchmarks:":[72],"Earnings-21":[73],"22,":[75],"CORAAL,":[76],"TED-LIUM3.":[78],"The":[79],"self-attention":[85],"local":[87],"attention":[88],"global":[90],"token":[91],"has":[92],"best":[94],"accuracy":[95],"compared":[96,102],"to":[97],"other":[98],"architectures.":[99],"also":[101],"CTC":[105],"RNNT":[107,120],"decoders":[108],"showed":[110],"that":[111],"CTC-based":[112],"are":[114],"more":[115],"robust":[116],"efficient":[118],"than":[119],"form":[123]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}