{"id":"https://openalex.org/W4408352433","doi":"https://doi.org/10.1109/icassp49660.2025.10890672","title":"voc2vec: A Foundation Model for Non-Verbal Vocalization","display_name":"voc2vec: A Foundation Model for Non-Verbal Vocalization","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352433","doi":"https://doi.org/10.1109/icassp49660.2025.10890672"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890672","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":"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/A5083365850","display_name":"Alkis Koudounas","orcid":"https://orcid.org/0000-0003-4386-0409"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alkis Koudounas","raw_affiliation_strings":["Politecnico di Torino,Turin,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Turin,Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078641012","display_name":"Moreno La Quatra","orcid":"https://orcid.org/0000-0001-8838-064X"},"institutions":[{"id":"https://openalex.org/I246010334","display_name":"Universit\u00e0 degli Studi di Enna Kore","ror":"https://ror.org/04vd28p53","country_code":"IT","type":"education","lineage":["https://openalex.org/I246010334"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Moreno La Quatra","raw_affiliation_strings":["Kore University of Enna,Enna,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kore University of Enna,Enna,Italy","institution_ids":["https://openalex.org/I246010334"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":["Universit&#x00E0; Degli Studi di Palermo,Palermo,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E0; Degli Studi di Palermo,Palermo,Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001695309","display_name":"Elena Baralis","orcid":"https://orcid.org/0000-0001-9231-467X"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elena Baralis","raw_affiliation_strings":["Politecnico di Torino,Turin,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Turin,Italy","institution_ids":["https://openalex.org/I177477856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2763,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94727944,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"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":0.9182000160217285,"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":0.9182000160217285,"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":0.9013000130653381,"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/foundation","display_name":"Foundation (evidence)","score":0.7775485515594482},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.622174859046936},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3763164281845093},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32990002632141113},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.06559470295906067}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.7775485515594482},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.622174859046936},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3763164281845093},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32990002632141113},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.06559470295906067},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890672","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"},{"id":"pmh:oai:iris.unipa.it:10447/694130","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/694130","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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/bookPart"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.41999998688697815,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1974597084","https://openalex.org/W2085662862","https://openalex.org/W2146334809","https://openalex.org/W2167700723","https://openalex.org/W2551548999","https://openalex.org/W2566935005","https://openalex.org/W2593116425","https://openalex.org/W2785952417","https://openalex.org/W2892071465","https://openalex.org/W2895625244","https://openalex.org/W2959143276","https://openalex.org/W3197580070","https://openalex.org/W3197970772","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4210836801","https://openalex.org/W4225299287","https://openalex.org/W4297510487","https://openalex.org/W4372259780","https://openalex.org/W4381249885","https://openalex.org/W4385607386","https://openalex.org/W4385823123","https://openalex.org/W4385823412","https://openalex.org/W4392903618","https://openalex.org/W4401597538","https://openalex.org/W4402112095","https://openalex.org/W4402669711","https://openalex.org/W4404295211","https://openalex.org/W6746278845","https://openalex.org/W6755207826","https://openalex.org/W6778883912","https://openalex.org/W6780218876","https://openalex.org/W6810007534","https://openalex.org/W6839551726"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2358060160","https://openalex.org/W2035483685"],"abstract_inverted_index":{"Speech":[0],"foundation":[1,33,65,113],"models":[2,12,34],"have":[3],"demonstrated":[4],"exceptional":[5],"capabilities":[6],"in":[7,102],"speech-related":[8],"tasks.":[9,146],"Nevertheless,":[10],"these":[11],"often":[13],"struggle":[14],"with":[15],"non-verbal":[16,48,72,78,93,103],"audio":[17,79,112],"data,":[18],"such":[19],"as":[20],"vocalizations,":[21],"baby":[22],"crying,":[23],"etc.,":[24],"which":[25],"are":[26],"critical":[27],"for":[28,71,144],"various":[29],"real-world":[30],"applications.":[31],"Audio":[32],"well":[35],"handle":[36],"non-speech":[37],"data":[38,74],"but":[39],"also":[40],"fail":[41],"to":[42,56],"capture":[43],"the":[44,58,131,134,139],"nuanced":[45],"features":[46],"of":[47,85,92,133],"human":[49,73],"sounds.":[50],"In":[51],"this":[52],"work,":[53],"we":[54],"aim":[55],"overcome":[57],"above":[59],"shortcoming":[60],"and":[61,106,111,123],"propose":[62],"a":[63,83],"novel":[64],"model,":[66],"termed":[67],"voc2vec,":[68],"specifically":[69],"designed":[70],"leveraging":[75],"exclusively":[76],"open-soruce":[77],"datasets.":[80,129],"We":[81],"employ":[82],"collection":[84],"10":[86],"datasets":[87],"covering":[88],"around":[89],"125":[90],"hours":[91],"audio.":[94],"Experimental":[95],"results":[96],"prove":[97],"that":[98],"voc2vec":[99,116,137],"is":[100,138],"effective":[101],"vocalization":[104,145],"classification,":[105],"it":[107],"outperforms":[108,118],"conventional":[109],"speech":[110],"models.":[114],"Moreover,":[115],"consistently":[117],"strong":[119],"baselines,":[120],"namely":[121],"OpenSmile":[122],"emotion2vec,":[124],"on":[125],"six":[126],"different":[127],"benchmark":[128],"To":[130],"best":[132],"authors\u2019":[135],"knowledge,":[136],"first":[140],"universal":[141],"representation":[142],"model":[143]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
