{"id":"https://openalex.org/W4224457787","doi":"https://doi.org/10.21437/interspeech.2022-38","title":"E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR","display_name":"E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4224457787","doi":"https://doi.org/10.21437/interspeech.2022-38"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-38","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-38","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5091738469","display_name":"W. Ronny Huang","orcid":"https://orcid.org/0009-0000-8136-5666"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"W. Ronny Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001306222","display_name":"Shuo-Yiin Chang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuo-Yiin Chang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050133412","display_name":"David Rybach","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Rybach","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tara Sainath","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032640894","display_name":"Rohit Prabhavalkar","orcid":"https://orcid.org/0000-0001-5331-6058"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohit Prabhavalkar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037066965","display_name":"Cal Peyser","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cal Peyser","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039693533","display_name":"Zhiyun Lu","orcid":"https://orcid.org/0000-0002-1733-4061"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyun Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5030888546","display_name":"Cyril Allauzen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cyril Allauzen","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":23,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4995","last_page":"4999"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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/T11309","display_name":"Music and Audio Processing","score":0.9976000189781189,"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":0.7807668447494507},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7100600004196167},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.640500545501709},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5468137860298157},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4977104961872101},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4831047058105469},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.46484678983688354},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44672971963882446},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.438356876373291},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4382178783416748},{"id":"https://openalex.org/keywords/false-alarm","display_name":"False alarm","score":0.41401129961013794},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37712907791137695},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3381943106651306},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2651536464691162},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1045142114162445}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7807668447494507},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7100600004196167},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.640500545501709},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5468137860298157},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4977104961872101},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4831047058105469},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.46484678983688354},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44672971963882446},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.438356876373291},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4382178783416748},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.41401129961013794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37712907791137695},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3381943106651306},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2651536464691162},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1045142114162445},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-38","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-38","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W3196421258","https://openalex.org/W4387301579","https://openalex.org/W2763956190","https://openalex.org/W3008587939","https://openalex.org/W4400488565","https://openalex.org/W4296070390"],"abstract_inverted_index":{"Improving":[0],"the":[1,30,77,89,106,124,162],"performance":[2],"of":[3,97,141],"end-to-end":[4,93],"ASR":[5,94],"models":[6],"on":[7,48,114,120,133,166],"long":[8],"utterances":[9],"ranging":[10],"from":[11,123],"minutes":[12],"to":[13,28,87,109,143,161],"hours":[14],"in":[15,21,32,76,101,156],"length":[16],"is":[17,27],"an":[18,80,92],"ongoing":[19],"challenge":[20],"speech":[22,60],"recognition.":[23],"A":[24],"common":[25],"solution":[26],"segment":[29,43,99],"audio":[31,137],"advance":[33],"using":[34],"a":[35,63,71,102,167],"separate":[36],"voice":[37],"activity":[38],"detector":[39],"(VAD)":[40],"that":[41,66],"decides":[42],"boundary":[44],"locations":[45],"based":[46],"purely":[47],"acoustic":[49,116],"speech/non-speech":[50],"information.":[51],"VAD":[52,90,163],"segmenters,":[53],"however,":[54],"may":[55,73],"be":[56,68,110],"sub-optimal":[57],"for":[58],"real-world":[59],"where,":[61],"e.g.,":[62],"complete":[64],"sentence":[65],"should":[67],"taken":[69],"as":[70],"whole":[72],"contain":[74],"hesitations":[75],"middle":[78],"(\"set":[79],"alarm":[81],"for...":[82],"5":[83],"o'clock\").":[84],"We":[85],"propose":[86],"replace":[88],"with":[91,127,139],"model":[95],"capable":[96],"predicting":[98],"boundaries":[100],"streaming":[103],"fashion,":[104],"allowing":[105],"segmentation":[107],"decision":[108],"conditioned":[111],"not":[112],"only":[113],"better":[115],"features":[117,122],"but":[118],"also":[119],"semantic":[121],"decoded":[125],"text":[126],"negligible":[128],"extra":[129],"computation.":[130],"In":[131],"experiments":[132],"real":[134],"world":[135],"long-form":[136],"(YouTube)":[138],"lengths":[140],"up":[142],"30":[144],"minutes,":[145],"we":[146],"demonstrate":[147],"8.5%":[148],"relative":[149],"WER":[150],"improvement":[151],"and":[152],"250":[153],"ms":[154],"reduction":[155],"median":[157],"end-of-segment":[158],"latency":[159],"compared":[160],"segmenter":[164],"baseline":[165],"state-of-the-art":[168],"Conformer":[169],"RNN-T":[170],"model.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}