{"id":"https://openalex.org/W4391021778","doi":"https://doi.org/10.1109/asru57964.2023.10389743","title":"Two-Pass Endpoint Detection for Speech Recognition","display_name":"Two-Pass Endpoint Detection for Speech Recognition","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021778","doi":"https://doi.org/10.1109/asru57964.2023.10389743"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5109046112","display_name":"Anirudh Raju","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anirudh Raju","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013650472","display_name":"Aparna Khare","orcid":"https://orcid.org/0000-0001-7151-3055"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aparna Khare","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017672130","display_name":"Di He","orcid":"https://orcid.org/0009-0008-5025-7062"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Di He","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064043969","display_name":"Ilya Sklyar","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ilya Sklyar","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100336360","display_name":"Long Chen","orcid":"https://orcid.org/0000-0001-6148-9709"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Long Chen","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093744039","display_name":"Sam Alptekin","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam Alptekin","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085746637","display_name":"Viet Anh Trinh","orcid":"https://orcid.org/0000-0002-1660-6627"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viet Anh Trinh","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442950","display_name":"Zhe Zhang","orcid":"https://orcid.org/0000-0001-8407-3167"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Zhang","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082491203","display_name":"Colin Vaz","orcid":"https://orcid.org/0000-0002-5709-7953"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Colin Vaz","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060593241","display_name":"Venkatesh Ravichandran","orcid":"https://orcid.org/0009-0001-7214-2919"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venkatesh Ravichandran","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090454997","display_name":"Roland Maas","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roland Maas","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110230355","display_name":"Ariya Rastrow","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ariya Rastrow","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5109046112"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.5063,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73154173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9993000030517578,"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":0.7482777833938599},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7322511076927185},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.717343807220459},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6695391535758972},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6271853446960449},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4727528989315033},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.42076346278190613},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4102241098880768},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4055558741092682},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33422479033470154},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11807131767272949},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.060993075370788574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7482777833938599},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7322511076927185},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.717343807220459},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6695391535758972},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6271853446960449},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4727528989315033},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.42076346278190613},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4102241098880768},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4055558741092682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33422479033470154},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11807131767272949},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.060993075370788574},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1536583098","https://openalex.org/W1903951673","https://openalex.org/W2048497537","https://openalex.org/W2143612262","https://openalex.org/W2147934395","https://openalex.org/W2402316076","https://openalex.org/W2406262283","https://openalex.org/W2625979394","https://openalex.org/W2783549597","https://openalex.org/W2891367150","https://openalex.org/W2892300106","https://openalex.org/W2935756939","https://openalex.org/W2963827914","https://openalex.org/W2973122799","https://openalex.org/W3015927303","https://openalex.org/W3100460087","https://openalex.org/W3143923103","https://openalex.org/W3149509723","https://openalex.org/W3163907627","https://openalex.org/W3196784225","https://openalex.org/W4221147513","https://openalex.org/W4224457787","https://openalex.org/W4226034529","https://openalex.org/W4297841778","https://openalex.org/W4375868951"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W4229451372"],"abstract_inverted_index":{"Endpoint":[0],"(EP)":[1],"detection":[2],"is":[3,58],"a":[4,42,54,61,78],"key":[5],"component":[6],"of":[7,35,104],"far-field":[8],"speech":[9],"recognition":[10],"systems":[11],"that":[12,98],"assist":[13],"the":[14,33,49,70,92,105],"user":[15],"through":[16],"voice":[17],"commands.":[18],"The":[19],"endpoint":[20,51],"detector":[21],"has":[22],"to":[23],"trade-off":[24,71],"between":[25,72],"accuracy":[26],"and":[27,75,91],"latency,":[28],"since":[29],"waiting":[30],"longer":[31],"reduces":[32],"cases":[34],"users":[36],"being":[37],"cut-off":[38],"early.":[39],"We":[40,96],"propose":[41],"novel":[43],"two-pass":[44],"solution":[45],"for":[46],"endpointing,":[47],"where":[48],"utterance":[50],"detected":[52],"from":[53],"first":[55],"pass":[56],"endpointer":[57],"verified":[59],"by":[60],"2nd-pass":[62],"model":[63,108],"termed":[64],"EP":[65,107],"Arbitrator.":[66],"Our":[67],"method":[68,100],"improves":[69],"early":[73],"cut-offs":[74],"latency":[76],"over":[77],"baseline":[79],"endpointer,":[80],"as":[81],"tested":[82],"on":[83],"datasets":[84],"including":[85],"voice-assistant":[86],"transactional":[87],"queries,":[88],"conversational":[89],"speech,":[90],"public":[93],"SLURP":[94],"corpus.":[95],"demonstrate":[97],"our":[99],"shows":[101],"improvements":[102],"regardless":[103],"first-pass":[106],"used.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}