{"id":"https://openalex.org/W4375869207","doi":"https://doi.org/10.1109/icassp49357.2023.10096595","title":"Dynamic Speech Endpoint Detection with Regression Targets","display_name":"Dynamic Speech Endpoint Detection with Regression Targets","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869207","doi":"https://doi.org/10.1109/icassp49357.2023.10096595"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5073588571","display_name":"Dawei Liang","orcid":"https://orcid.org/0000-0002-4406-4108"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dawei Liang","raw_affiliation_strings":["University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341891","display_name":"Hang Su","orcid":"https://orcid.org/0000-0002-6877-6783"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hang Su","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021272981","display_name":"T. P. Singh","orcid":"https://orcid.org/0000-0002-9375-3495"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tarun Singh","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074237839","display_name":"Jay Mahadeokar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jay Mahadeokar","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043881011","display_name":"Shanil Puri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shanil Puri","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050766674","display_name":"Jiedan Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiedan Zhu","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025977484","display_name":"Edison Thomaz","orcid":"https://orcid.org/0000-0001-8188-0457"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edison Thomaz","raw_affiliation_strings":["University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113773386","display_name":"Mike Seltzer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mike Seltzer","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5073588571"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":0.869,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78164991,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T12031","display_name":"Speech and dialogue systems","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/T12128","display_name":"AI in Service Interactions","score":0.9988999962806702,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976999759674072,"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":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8498936891555786},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6093364357948303},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5501565933227539},{"id":"https://openalex.org/keywords/wearable-computer","display_name":"Wearable computer","score":0.5171625018119812},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.4836772382259369},{"id":"https://openalex.org/keywords/pointer","display_name":"Pointer (user interface)","score":0.47919711470603943},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4264480173587799},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.41766971349716187},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3373493552207947},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3331310749053955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3167971968650818},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28892260789871216},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.15769073367118835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8498936891555786},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6093364357948303},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5501565933227539},{"id":"https://openalex.org/C150594956","wikidata":"https://www.wikidata.org/wiki/Q1334829","display_name":"Wearable computer","level":2,"score":0.5171625018119812},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4836772382259369},{"id":"https://openalex.org/C150202949","wikidata":"https://www.wikidata.org/wiki/Q107602","display_name":"Pointer (user interface)","level":2,"score":0.47919711470603943},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4264480173587799},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.41766971349716187},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3373493552207947},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3331310749053955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3167971968650818},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28892260789871216},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.15769073367118835},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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:10.1109/icassp49357.2023.10096595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W15516501","https://openalex.org/W1522301498","https://openalex.org/W1837709900","https://openalex.org/W1903951673","https://openalex.org/W1932883564","https://openalex.org/W2064675550","https://openalex.org/W2625979394","https://openalex.org/W2742061524","https://openalex.org/W2787712888","https://openalex.org/W2890735031","https://openalex.org/W2891367150","https://openalex.org/W2892300106","https://openalex.org/W2935756939","https://openalex.org/W3015219049","https://openalex.org/W3143923103","https://openalex.org/W3160042174","https://openalex.org/W4221141775","https://openalex.org/W4295312788","https://openalex.org/W6631190155","https://openalex.org/W6766978945","https://openalex.org/W6810009947"],"related_works":["https://openalex.org/W2387387477","https://openalex.org/W2394051415","https://openalex.org/W4388218401","https://openalex.org/W4255928847","https://openalex.org/W2352114091","https://openalex.org/W121845590","https://openalex.org/W4241809317","https://openalex.org/W2379950384","https://openalex.org/W123216772","https://openalex.org/W3172030588"],"abstract_inverted_index":{"Interactive":[0],"voice":[1,38],"assistants":[2,39],"have":[3],"been":[4],"widely":[5],"used":[6],"as":[7],"input":[8],"interfaces":[9],"in":[10,140],"various":[11],"scenarios,":[12],"e.g.":[13],"on":[14,20,49,79,100],"smart":[15],"home":[16],"devices,":[17],"wearables":[18,107],"and":[19,92,106,119,135],"AR":[21],"devices.":[22],"Detecting":[23],"the":[24,80,123,130,138,141],"end":[25],"of":[26,82,132,137],"a":[27,63,88,113],"speech":[28,31,45,66,108],"query,":[29],"i.e.":[30],"end-pointing,":[32],"is":[33,47],"an":[34,71],"important":[35],"task":[36],"for":[37,96],"to":[40,73,122],"interact":[41],"with":[42,54,103],"users.":[43],"Traditionally,":[44],"end-pointing":[46,67,117],"based":[48,78],"pure":[50],"classification":[51],"methods":[52],"along":[53],"arbitrary":[55],"binary":[56],"targets.":[57],"In":[58],"this":[59,133],"paper,":[60],"we":[61,86],"propose":[62],"novel":[64],"regression-based":[65],"model,":[68],"which":[69],"enables":[70],"end-pointer":[72],"adjust":[74],"its":[75,94],"detection":[76],"behavior":[77],"context":[81],"user":[83],"queries.":[84],"Specifically,":[85],"present":[87],"pause":[89],"modeling":[90],"method":[91],"show":[93],"effectiveness":[95],"dynamic":[97],"end-pointing.":[98],"Based":[99],"our":[101,110],"experiments":[102],"vendor-collected":[104],"smartphone":[105],"queries,":[109],"strategy":[111],"shows":[112],"better":[114],"trade-off":[115],"between":[116],"latency":[118],"accuracy,":[120],"compared":[121],"traditional":[124],"classification-based":[125],"method.":[126],"We":[127],"further":[128],"discuss":[129],"benefits":[131],"model":[134],"generalization":[136],"framework":[139],"paper.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}