{"id":"https://openalex.org/W4392904263","doi":"https://doi.org/10.1109/icassp48485.2024.10447653","title":"Self-Supervised Pretraining for Robust Personalized Voice Activity Detection in Adverse Conditions","display_name":"Self-Supervised Pretraining for Robust Personalized Voice Activity Detection in Adverse Conditions","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904263","doi":"https://doi.org/10.1109/icassp48485.2024.10447653"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5055991258","display_name":"Holger Severin Bovbjerg","orcid":"https://orcid.org/0000-0002-8735-739X"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Holger Severin Bovbjerg","raw_affiliation_strings":["Aalborg University,Department of Electronic Systems,Denmark","Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Department of Electronic Systems,Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101679595","display_name":"Jesper Jensen","orcid":"https://orcid.org/0000-0003-1478-622X"},"institutions":[{"id":"https://openalex.org/I4210130492","display_name":"Oticon Medical (Denmark)","ror":"https://ror.org/03c5ds320","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210130492"]},{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jesper Jensen","raw_affiliation_strings":["Aalborg University,Department of Electronic Systems,Denmark","Oticon A/S, Denmark","Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Department of Electronic Systems,Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Oticon A/S, Denmark","institution_ids":["https://openalex.org/I4210130492"]},{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023894109","display_name":"Jan \u00d8stergaard","orcid":"https://orcid.org/0000-0002-3724-6114"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jan \u00d8stergaard","raw_affiliation_strings":["Aalborg University,Department of Electronic Systems,Denmark","Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Department of Electronic Systems,Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["Aalborg University,Department of Electronic Systems,Denmark","Pioneer Centre for AI, Denmark","Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Department of Electronic Systems,Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Pioneer Centre for AI, Denmark","institution_ids":[]},{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10126","last_page":"10130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.998199999332428,"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":0.7467602491378784},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6834770441055298},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6168301105499268},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5561827421188354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5318595767021179},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.49483197927474976},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.49431848526000977},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4887833297252655},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4375545382499695},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4254639744758606},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4128662645816803},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32612621784210205},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31808164715766907},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.13150179386138916},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0691649317741394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7467602491378784},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6834770441055298},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6168301105499268},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5561827421188354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5318595767021179},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.49483197927474976},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.49431848526000977},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4887833297252655},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4375545382499695},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4254639744758606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4128662645816803},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32612621784210205},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31808164715766907},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.13150179386138916},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0691649317741394},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/073f7701-097d-46b8-8268-5c26a98b926a","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/073f7701-097d-46b8-8268-5c26a98b926a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1485222997","https://openalex.org/W1494198834","https://openalex.org/W2175298729","https://openalex.org/W2586068394","https://openalex.org/W2696967604","https://openalex.org/W2747874407","https://openalex.org/W2954930777","https://openalex.org/W2962788625","https://openalex.org/W2972943112","https://openalex.org/W2981087920","https://openalex.org/W2995181338","https://openalex.org/W3016011332","https://openalex.org/W3024085360","https://openalex.org/W3025260599","https://openalex.org/W3036601975","https://openalex.org/W3153215492","https://openalex.org/W3163621198","https://openalex.org/W3195050710","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4223655162","https://openalex.org/W4294068504","https://openalex.org/W4296960740","https://openalex.org/W6780218876","https://openalex.org/W6802388392","https://openalex.org/W6809805911","https://openalex.org/W6843659118"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W4294771049","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W1523214805","https://openalex.org/W4411210718","https://openalex.org/W2168417340","https://openalex.org/W4229451372","https://openalex.org/W2113211312"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4,53],"the":[5,18,39,60,64],"use":[6],"of":[7,20,57,62,66,85],"self-supervised":[8,101],"pretraining":[9,102],"on":[10,75],"a":[11,21,33,54,93],"large":[12],"unlabelled":[13],"data":[14],"set":[15],"to":[16,92,118,122],"improve":[17],"performance":[19,106],"personalized":[22,49,67],"voice":[23],"activity":[24],"detection":[25],"(VAD)":[26],"model":[27],"in":[28,107],"adverse":[29,119],"conditions.":[30],"We":[31,51],"pretrain":[32],"long":[34],"short-term":[35],"memory":[36],"(LSTM)-encoder":[37],"using":[38],"autoregressive":[40],"predictive":[41],"coding":[42],"(APC)":[43],"framework":[44],"and":[45,79,90],"fine-tune":[46],"it":[47],"for":[48],"VAD.":[50,68],"also":[52,111],"denoising":[55],"variant":[56],"APC,":[58],"with":[59],"goal":[61],"improving":[63],"robustness":[65],"The":[69],"trained":[70],"models":[71,113],"are":[72,115],"systematically":[73],"evaluated":[74],"both":[76],"clean":[77,108],"speech":[78,80],"contaminated":[81],"by":[82],"various":[83],"types":[84],"noise":[86],"at":[87],"different":[88],"SNR-levels":[89],"compared":[91,121],"purely":[94,123],"supervised":[95,124],"model.":[96],"Our":[97],"experiments":[98],"show":[99],"that":[100],"not":[103],"only":[104],"improves":[105],"conditions,":[109],"but":[110],"yields":[112],"which":[114],"more":[116],"robust":[117],"conditions":[120],"learning.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}