{"id":"https://openalex.org/W4408345768","doi":"https://doi.org/10.1109/icassp49660.2025.10889317","title":"Multi-Feature Audio Fusion for Nonverbal Vocalization Classification","display_name":"Multi-Feature Audio Fusion for Nonverbal Vocalization Classification","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345768","doi":"https://doi.org/10.1109/icassp49660.2025.10889317"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5028892629","display_name":"Siddhant Bikram Shah","orcid":"https://orcid.org/0009-0000-9403-8728"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]},{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhant Bikram Shah","raw_affiliation_strings":["Northeastern University,Department of Electrical and Computer Engineering,Boston,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,Department of Electrical and Computer Engineering,Boston,USA","institution_ids":["https://openalex.org/I111088046","https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087824302","display_name":"Kristina T. Johnson","orcid":"https://orcid.org/0000-0003-4568-2060"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]},{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristina T. Johnson","raw_affiliation_strings":["Northeastern University,Department of Electrical and Computer Engineering Department of Communication Sciences and Disorders,Boston,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,Department of Electrical and Computer Engineering Department of Communication Sciences and Disorders,Boston,USA","institution_ids":["https://openalex.org/I111088046","https://openalex.org/I12912129"]}]}],"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":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10860","display_name":"Speech and Audio Processing","score":0.9894999861717224,"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":0.9894999861717224,"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":0.9768999814987183,"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":0.9621000289916992,"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":0.7229779958724976},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5951858162879944},{"id":"https://openalex.org/keywords/nonverbal-communication","display_name":"Nonverbal communication","score":0.5787030458450317},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5658184289932251},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.537020742893219},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.48966529965400696},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.429551362991333},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38242924213409424},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.1561821699142456},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10471180081367493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7229779958724976},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5951858162879944},{"id":"https://openalex.org/C145633318","wikidata":"https://www.wikidata.org/wiki/Q207125","display_name":"Nonverbal communication","level":2,"score":0.5787030458450317},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5658184289932251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.537020742893219},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.48966529965400696},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.429551362991333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38242924213409424},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.1561821699142456},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10471180081367493},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2024635814","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2964243274","https://openalex.org/W3100732527","https://openalex.org/W3133207760","https://openalex.org/W3158929093","https://openalex.org/W4309969875","https://openalex.org/W4379193822","https://openalex.org/W4385607386","https://openalex.org/W4392909502","https://openalex.org/W4396753653","https://openalex.org/W6637373629","https://openalex.org/W6780218876","https://openalex.org/W6781150751","https://openalex.org/W6783437975","https://openalex.org/W6784333009","https://openalex.org/W6788328058"],"related_works":["https://openalex.org/W2391422698","https://openalex.org/W52595306","https://openalex.org/W2385209118","https://openalex.org/W4299362043","https://openalex.org/W1522611117","https://openalex.org/W4236235619","https://openalex.org/W2354814076","https://openalex.org/W2570142844","https://openalex.org/W2354776243","https://openalex.org/W4312974229"],"abstract_inverted_index":{"Nonverbal":[0],"vocalizations":[1,33,186,214,239],"serve":[2],"an":[3,107],"essential":[4],"role":[5],"in":[6,131,143,148,163,173,236],"general":[7],"communication":[8,38],"and":[9,11,18,23,29,39,59,62,88,122,129,170,196,259],"expression,":[10],"they":[12,63],"are":[13,34],"particularly":[14],"integral":[15],"for":[16,36,111,185,246],"non-":[17],"minimally-speaking":[19],"individuals":[20],"with":[21,188,251],"autism":[22],"other":[24],"neurodevelopmental":[25],"disorders.":[26],"Accurate":[27],"analysis":[28],"classification":[30,114,120,181],"of":[31,43,81,109,168,183,204],"these":[32,205],"crucial":[35],"enhancing":[37],"deepening":[40],"our":[41],"understanding":[42],"this":[44],"underserved":[45],"population.":[46],"However,":[47],"most":[48],"audio-processing":[49],"machine-learning":[50],"techniques":[51],"rely":[52],"on":[53],"linguistic":[54],"cues":[55],"like":[56],"speech":[57],"fluency":[58],"word":[60],"pronunciation,":[61],"do":[64],"not":[65,231],"generalize":[66],"well":[67],"to":[68,218],"nonverbal":[69,238],"vocalizations.":[70],"We":[71,150,176],"propose":[72],"a":[73,144,153,159,179,193,243],"multi-level":[74],"fusion":[75,258],"network":[76],"that":[77],"combines":[78],"three":[79],"types":[80],"audio":[82,119,134,254],"features":[83],"\u2013":[84,91],"Wav2Vec2":[85],"representations,":[86],"mel-spectrograms,":[87],"low-level":[89],"descriptors":[90],"using":[92,215],"6,551":[93],"samples":[94],"across":[95],"7":[96],"vocalization":[97],"classes":[98],"from":[99],"the":[100,112,132,166,202,210,223],"open-access":[101],"ReCANVo":[102],"dataset.":[103],"The":[104],"model":[105],"achieves":[106],"accuracy":[108,182],"64.09%":[110],"7-class":[113],"task,":[115],"outperforming":[116],"8":[117],"traditional":[118],"methods":[121],"3":[123],"feature-fusion":[124],"approaches.":[125],"To":[126],"address":[127],"heterogeneity":[128],"noise":[130],"real-world":[133,253],"data,":[135,255],"we":[136,208],"tested":[137],"four":[138],"sample":[139,260],"augmentation":[140],"techniques,":[141],"resulting":[142],"14%":[145],"relative":[146,161],"increase":[147,162],"accuracy.":[149],"further":[151],"examined":[152],"single":[154],"individual":[155],"(1,595":[156],"samples),":[157],"obtaining":[158],"6.29%":[160],"accuracy,":[164],"highlighting":[165],"effects":[167],"speaker":[169],"environment":[171],"variability":[172],"population-level":[174],"models.":[175],"also":[177,241],"achieved":[178],"binary":[180],"85.80%":[184],"associated":[187],"positive/negative":[189],"affective":[190],"states,":[191],"suggesting":[192],"potentially":[194],"robust":[195],"highly":[197],"separable":[198],"latent":[199],"structure":[200],"underlying":[201],"valence":[203],"sounds.":[206],"Finally,":[207],"quantified":[209],"inter-class":[211],"relationships":[212],"between":[213,226],"cosine":[216],"similarity":[217],"offer":[219],"additional":[220],"insights":[221],"into":[222],"acoustic":[224],"patterns":[225],"classes.":[227],"Our":[228],"exploratory":[229],"study":[230],"only":[232],"uncovers":[233],"key":[234],"challenges":[235],"processing":[237],"but":[240],"provides":[242],"foundational":[244],"framework":[245],"future":[247],"machine":[248],"learning":[249],"research":[250],"rare,":[252],"including":[256],"multi-feature":[257],"augmentation.":[261]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}