乐胖代购免代理版

{"id":"https://openalex.org/W4360601747","doi":"https://doi.org/10.48550/arxiv.2204.10749","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":"2022-01-01","ids":{"openalex":"https://openalex.org/W4360601747","doi":"https://doi.org/10.48550/arxiv.2204.10749"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2204.10749","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"posted-content","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/2204.10749","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091738469","display_name":"W. Ronny Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, W. Ronny","raw_affiliation_strings":[],"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":"Chang, Shuo-yiin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050133412","display_name":"David Rybach","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rybach, David","raw_affiliation_strings":[],"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":"Prabhavalkar, Rohit","raw_affiliation_strings":[],"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":"Sainath, Tara N.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030888546","display_name":"Cyril Allauzen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Allauzen, Cyril","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037066965","display_name":"Cal Peyser","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peyser, Cal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","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":"Lu, Zhiyun","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"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":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":59},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998,"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":0.9998,"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":0.9983,"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":0.9976,"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/market-segmentation","display_name":"Market Segmentation","score":0.5214881},{"id":"https://openalex.org/keywords/false-alarm","display_name":"False alarm","score":0.45825234},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.43564123}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7312777},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.68457526},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.68022656},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.57596254},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.5214881},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.49130955},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4585985},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.45825234},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.45733103},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.43564123},{"id":"https://openalex.org/C2779119184","wikidata":"https://www.wikidata.org/wiki/Q294350","display_name":"ALARM","level":2,"score":0.41561788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33117783},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10815045},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07899779},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2204.10749","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://api.datacite.org/dois/10.48550/arxiv.2204.10749","pdf_url":null,"source":{"id":"https://openalex.org/S4393179698","display_name":"DataCite API","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I4210145204","host_organization_name":"DataCite","host_organization_lineage":["https://openalex.org/I4210145204"],"host_organization_lineage_names":["DataCite"],"type":"metadata"},"license":null,"license_id":null,"version":null}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2204.10749","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"score":0.77,"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4379535633","https://openalex.org/W3179968364","https://openalex.org/W3121346907","https://openalex.org/W3037375888","https://openalex.org/W2732807254","https://openalex.org/W2731305060","https://openalex.org/W2587670262","https://openalex.org/W2372003537","https://openalex.org/W2366730739","https://openalex.org/W1584123598"],"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]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4360601747","counts_by_year":[],"updated_date":"2025-03-04T16:40:57.682483","created_date":"2023-03-24"}