{"id":"https://openalex.org/W4391021572","doi":"https://doi.org/10.1109/asru57964.2023.10389645","title":"Efficient Cascaded Streaming ASR System Via Frame Rate Reduction","display_name":"Efficient Cascaded Streaming ASR System Via Frame Rate Reduction","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021572","doi":"https://doi.org/10.1109/asru57964.2023.10389645"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389645","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5013075695","display_name":"Xingyu Cai","orcid":"https://orcid.org/0000-0003-1537-7161"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xingyu Cai","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079902855","display_name":"David Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Qiu","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058886181","display_name":"Shaojin Ding","orcid":"https://orcid.org/0000-0002-2108-3111"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaojin Ding","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014088530","display_name":"Dongseong Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongseong Hwang","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093745492","display_name":"Weiran Wang Antoine Bruguier","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiran Wang Antoine Bruguier","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032640894","display_name":"Rohit Prabhavalkar","orcid":"https://orcid.org/0000-0001-5331-6058"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohit Prabhavalkar","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara Sainath","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101319167","display_name":"Yanzhang He","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanzhang He","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.471,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.601087,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":67,"max":78},"biblio":{"volume":"33","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9952,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9952,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9931,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9886,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7015861},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.69119006},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.58777237},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.24420509},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07324839},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389645","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.64,"id":"https://metadata.un.org/sdg/7"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":30,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W2160815625","https://openalex.org/W2327501763","https://openalex.org/W2515439472","https://openalex.org/W2525778437","https://openalex.org/W2617258110","https://openalex.org/W2620947159","https://openalex.org/W2889012072","https://openalex.org/W2936774411","https://openalex.org/W2962760690","https://openalex.org/W2963747784","https://openalex.org/W2964539095","https://openalex.org/W2973122799","https://openalex.org/W3015194534","https://openalex.org/W3033188311","https://openalex.org/W3094667432","https://openalex.org/W3095311338","https://openalex.org/W3096686110","https://openalex.org/W3097777922","https://openalex.org/W3160766462","https://openalex.org/W3163203022","https://openalex.org/W3163793923","https://openalex.org/W3196733780","https://openalex.org/W3197976839","https://openalex.org/W3211278025","https://openalex.org/W4223655162","https://openalex.org/W4223988178","https://openalex.org/W4372267461","https://openalex.org/W4388017359"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2530322880","https://openalex.org/W2390279801","https://openalex.org/W2382290278","https://openalex.org/W2376932109","https://openalex.org/W2359140296","https://openalex.org/W2358668433","https://openalex.org/W2350741829","https://openalex.org/W2001405890","https://openalex.org/W1596801655"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,58,105],"explore":[4],"various":[5],"frame":[6,30,64,110],"rate":[7,31,65,111],"reduction":[8,32,79],"schemes":[9],"on":[10,29,93],"the":[11,22,55,61,71,94,109,120,139],"two-pass":[12],"cascaded":[13],"encoder":[14],"model":[15],"to":[16,66,112],"improve":[17],"its":[18],"efficiency":[19],"without":[20,91],"scarifying":[21],"transcription":[23],"quality.":[24],"We":[25],"conduct":[26],"extensive":[27],"studies":[28],"strategies,":[33],"left":[34],"and":[35,45,48,123],"right":[36],"context":[37],"window":[38],"length,":[39],"trade-offs":[40],"in":[41,50],"quality,":[42],"latency,":[43,90],"computation":[44],"power":[46,83,130],"consumption,":[47],"performance":[49],"short-and":[51],"long-form":[52],"datasets.":[53],"With":[54],"proposed":[56],"schemes,":[57],"can":[59,106],"lower":[60,88],"2nd":[62],"pass":[63],"$120":[67],"\\mathrm{~ms}$,":[68],"half":[69],"of":[70],"1st":[72,121],"pass's.":[73],"This":[74],"achieves":[75],"$20":[76],"\\%$":[77,82,87,126],"RTF":[78,127],"/":[80,85,128],"$13":[81],"saving":[84],"$19":[86],"final":[89],"impact":[92],"word-error-rate":[95],"nor":[96],"partial":[97,102],"results'":[98],"latency.":[99],"If":[100],"allowing":[101],"latency":[103],"increase,":[104],"further":[107],"reduce":[108],"$180":[113],"\\mathrm{~ms}$":[114,118],"or":[115,135],"even":[116,136],"$240":[117],"from":[119],"pass,":[122],"obtain":[124],"$45":[125],"35%":[129],"savings,":[131],"with":[132],"a":[133],"similar":[134],"better":[137],"(on":[138],"short-form":[140],"testset)":[141],"recognition":[142],"accuracy.":[143]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4391021572","counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-01-03T08:11:21.894137","created_date":"2024-01-20"}