{"id":"https://openalex.org/W3196296753","doi":"https://doi.org/10.21437/interspeech.2021-1977","title":"A Lightweight Framework for Online Voice Activity Detection in the Wild","display_name":"A Lightweight Framework for Online Voice Activity Detection in the Wild","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196296753","doi":"https://doi.org/10.21437/interspeech.2021-1977","mag":"3196296753"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1977","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1977","pdf_url":"https://www.isca-archive.org/interspeech_2021/xu21b_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2021/xu21b_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025827045","display_name":"Xuenan Xu","orcid":"https://orcid.org/0000-0001-8718-1278"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuenan Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080154283","display_name":"Heinrich Dinkel","orcid":"https://orcid.org/0000-0003-4330-8980"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heinrich Dinkel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081865665","display_name":"Mengyue Wu","orcid":"https://orcid.org/0000-0002-5599-8707"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengyue Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Yu","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":0.5989,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.66240356,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"371","last_page":"375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9990000128746033,"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":0.9962999820709229,"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":0.6503965854644775},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5358807444572449},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3946989178657532},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.1907631754875183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6503965854644775},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5358807444572449},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3946989178657532},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.1907631754875183}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1977","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1977","pdf_url":"https://www.isca-archive.org/interspeech_2021/xu21b_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2021-1977","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1977","pdf_url":"https://www.isca-archive.org/interspeech_2021/xu21b_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3196296753.pdf","grobid_xml":"https://content.openalex.org/works/W3196296753.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1985242443","https://openalex.org/W1999454387","https://openalex.org/W2023582935","https://openalex.org/W2048497537","https://openalex.org/W2126693545","https://openalex.org/W2142170306","https://openalex.org/W2408468399","https://openalex.org/W2792351646","https://openalex.org/W2884011836","https://openalex.org/W2888930363","https://openalex.org/W2892300106","https://openalex.org/W2970971581","https://openalex.org/W2981728176","https://openalex.org/W2995588677","https://openalex.org/W3013492814","https://openalex.org/W3015383801","https://openalex.org/W3016059657","https://openalex.org/W3048911900","https://openalex.org/W3096625841","https://openalex.org/W3096787456","https://openalex.org/W3124216180"],"related_works":["https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W2106462793","https://openalex.org/W2099105119","https://openalex.org/W2559837139","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2081671587","https://openalex.org/W1151175420","https://openalex.org/W2131711534"],"abstract_inverted_index":{"Voice":[0],"activity":[1],"detection":[2],"(VAD)":[3],"is":[4],"an":[5],"essential":[6],"pre-processing":[7],"component":[8],"for":[9,24,54,118],"speech-related":[10],"tasks":[11],"such":[12],"as":[13],"automatic":[14],"speech":[15],"recognition":[16],"(ASR).Traditional":[17],"VAD":[18,35],"systems":[19],"require":[20],"strong":[21],"frame-level":[22],"supervision":[23,74],"training,":[25],"inhibiting":[26],"their":[27],"performance":[28],"in":[29],"real-world":[30,99],"test":[31,93],"scenarios.Previously,":[32],"the":[33,59,108],"generalpurpose":[34],"(GPVAD)":[36],"framework":[37],"has":[38],"been":[39],"proposed":[40,85],"to":[41,75],"enhance":[42],"noise":[43],"robustness":[44],"significantly.However,":[45],"GPVAD":[46,90],"models":[47,88],"are":[48],"comparatively":[49],"large":[50],"and":[51,98,110],"only":[52,104],"work":[53,57],"offline":[55],"evaluation.This":[56],"proposes":[58],"use":[60],"of":[61,107,114],"a":[62,67,76,123],"knowledge":[63],"distillation":[64],"framework,":[65],"where":[66],"(large,":[68],"offline)":[69],"teacher":[70,116],"model":[71,103,117],"provides":[72],"framelevel":[73],"(light,":[77],"online)":[78],"student":[79,87,102],"model.Our":[80],"experiments":[81],"verify":[82],"that":[83],"our":[84,115],"lightweight":[86],"outperform":[89],"on":[91,122],"all":[92],"sets,":[94],"including":[95],"clean,":[96],"synthetic":[97],"scenarios.Our":[100],"smallest":[101],"uses":[105],"2.2%":[106],"parameters":[109],"15.9%":[111],"duration":[112],"cost":[113],"inference":[119],"when":[120],"evaluated":[121],"Raspberry":[124],"Pi.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}