{"id":"https://openalex.org/W4385822277","doi":"https://doi.org/10.21437/interspeech.2023-460","title":"Towards Robust Family-Infant Audio Analysis Based on Unsupervised Pretraining of Wav2vec 2.0 on Large-Scale Unlabeled Family Audio","display_name":"Towards Robust Family-Infant Audio Analysis Based on Unsupervised Pretraining of Wav2vec 2.0 on Large-Scale Unlabeled Family Audio","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822277","doi":"https://doi.org/10.21437/interspeech.2023-460","pmid":"https://pubmed.ncbi.nlm.nih.gov/41659017"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-460","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100456945","display_name":"Jialu Li","orcid":"https://orcid.org/0000-0003-0092-8071"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jialu Li","raw_affiliation_strings":["Beckman Institute for Advanced Science and Technology, University of Illinois","Department of Electrical and Computer Engineering, University of Illinois"],"affiliations":[{"raw_affiliation_string":"Beckman Institute for Advanced Science and Technology, University of Illinois","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Beckman Institute for Advanced Science and Technology, University of Illinois","Department of Electrical and Computer Engineering, University of Illinois"],"affiliations":[{"raw_affiliation_string":"Beckman Institute for Advanced Science and Technology, University of Illinois","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040993718","display_name":"Nancy L. McElwain","orcid":"https://orcid.org/0000-0001-9586-5020"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nancy L. McElwain","raw_affiliation_strings":["Beckman Institute for Advanced Science and Technology, University of Illinois","Department of Human Development and Family Studies, University of Illinois"],"affiliations":[{"raw_affiliation_string":"Beckman Institute for Advanced Science and Technology, University of Illinois","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Human Development and Family Studies, University of Illinois","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100456945"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":2.3058,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89281959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"2023","issue":null,"first_page":"1035","last_page":"1039"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9940999746322632,"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/T11309","display_name":"Music and Audio Processing","score":0.9940999746322632,"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/T10860","display_name":"Speech and Audio Processing","score":0.9868000149726868,"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":0.9776999950408936,"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":0.6240825653076172},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5375359654426575},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.46547409892082214},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4531169831752777},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.44017547369003296},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.3963100016117096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3692384362220764},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3211538791656494},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2563523054122925},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.049273014068603516}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6240825653076172},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5375359654426575},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.46547409892082214},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4531169831752777},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.44017547369003296},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.3963100016117096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3692384362220764},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3211538791656494},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2563523054122925},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.049273014068603516},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2023-460","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmid:41659017","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41659017","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech","raw_type":null},{"id":"pmh:oai:europepmc.org:11682860","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12875392","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":"Text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1993458811","https://openalex.org/W2082322470","https://openalex.org/W2149621653","https://openalex.org/W2176625348","https://openalex.org/W2191779130","https://openalex.org/W2219249508","https://openalex.org/W2294879375","https://openalex.org/W2321019691","https://openalex.org/W2609286886","https://openalex.org/W2696967604","https://openalex.org/W2889288729","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2972389587","https://openalex.org/W2973049979","https://openalex.org/W2973193289","https://openalex.org/W3024869864","https://openalex.org/W3031133340","https://openalex.org/W3036601975","https://openalex.org/W3045184637","https://openalex.org/W3143367551","https://openalex.org/W3167533889","https://openalex.org/W3174716293","https://openalex.org/W3196025297","https://openalex.org/W3197642003","https://openalex.org/W3206102693","https://openalex.org/W3206710901","https://openalex.org/W3207911573","https://openalex.org/W3208966620","https://openalex.org/W3216401400","https://openalex.org/W4224252851","https://openalex.org/W4226074601","https://openalex.org/W4285044984","https://openalex.org/W4286841926","https://openalex.org/W4296068438","https://openalex.org/W4308216321","https://openalex.org/W4375869379"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W1828907027","https://openalex.org/W1996547972","https://openalex.org/W1975359510","https://openalex.org/W1603949574","https://openalex.org/W2379113420","https://openalex.org/W2604447241","https://openalex.org/W2748661748","https://openalex.org/W2921688766","https://openalex.org/W1985168493"],"abstract_inverted_index":{"To":[0],"perform":[1],"automatic":[2],"family":[3,55],"audio":[4,41,56,89],"analysis,":[5],"past":[6],"studies":[7],"have":[8],"collected":[9],"recordings":[10,81],"using":[11,76],"phone,":[12],"video,":[13],"or":[14,26],"audio-only":[15],"recording":[16],"devices":[17],"like":[18],"LENA,":[19],"investigated":[20],"supervised":[21],"learning":[22,54],"methods,":[23],"and":[24,97,107,114,118,129,135],"used":[25],"fine-tuned":[27],"general-purpose":[28],"embeddings":[29],"learned":[30],"from":[31],"large":[32],"pretrained":[33,75,85],"models.":[34],"In":[35],"this":[36],"study,":[37],"we":[38,122],"advance":[39],"the":[40],"component":[42],"of":[43,69,78,92],"a":[44,66],"new":[45],"infant":[46],"wearable":[47],"multi-modal":[48],"device":[49],"called":[50],"LittleBeats":[51],"(LB)":[52],"by":[53],"representation":[57],"via":[58],"wav2vec":[59],"2.0":[60],"(W2V2)":[61],"pretraining.":[62],"We":[63],"show":[64],"given":[65],"limited":[67],"number":[68],"labeled":[70,108],"LB":[71],"home":[72,80],"recordings,":[73],"W2V2":[74,84,112],"1k-hour":[77],"unlabeled":[79,88,106],"outperforms":[82],"oracle":[83],"on":[86,127,132],"52k-hour":[87],"in":[90],"terms":[91],"parent/infant":[93],"speaker":[94],"diarization":[95],"(SD)":[96],"vocalization":[98],"classifications":[99],"(VC)":[100],"at":[101],"home.":[102],"Extra":[103],"relevant":[104],"external":[105],"data":[109],"further":[110],"benefit":[111],"pretraining":[113],"fine-tuning.":[115],"With":[116],"SpecAug":[117],"environmental":[119],"speech":[120],"corruptions,":[121],"obtain":[123],"12%":[124],"relative":[125],"gain":[126],"SD":[128],"moderate":[130],"boost":[131],"VC.":[133],"Code":[134],"model":[136],"weights":[137],"are":[138],"available.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2023-08-15T00:00:00"}