{"id":"https://openalex.org/W4402111518","doi":"https://doi.org/10.21437/interspeech.2024-1315","title":"ParaCLAP \u2013 Towards a general language-audio model for computational paralinguistic tasks","display_name":"ParaCLAP \u2013 Towards a general language-audio model for computational paralinguistic tasks","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111518","doi":"https://doi.org/10.21437/interspeech.2024-1315"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1315","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1315","pdf_url":"https://www.isca-archive.org/interspeech_2024/jing24b_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2024/jing24b_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101414146","display_name":"Xin Jing","orcid":"https://orcid.org/0000-0002-3425-3968"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Jing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012240826","display_name":"Andreas Triantafyllopoulos","orcid":"https://orcid.org/0000-0001-8338-617X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Triantafyllopoulos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn Schuller","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":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1155","last_page":"1159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9884999990463257,"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":0.9884999990463257,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9477999806404114,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9311000108718872,"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/paralanguage","display_name":"Paralanguage","score":0.9874069690704346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7659116983413696},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4501788020133972},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41873055696487427},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32698166370391846},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2343026101589203}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.9874069690704346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7659116983413696},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4501788020133972},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41873055696487427},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32698166370391846},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2343026101589203},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-1315","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1315","pdf_url":"https://www.isca-archive.org/interspeech_2024/jing24b_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-1315","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1315","pdf_url":"https://www.isca-archive.org/interspeech_2024/jing24b_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7189395530","display_name":"Agentenbasierte, Interaktive, Tiefe 0shotlearningNetzwerke zur Optimierung von Ontologischem Klangverst\u00e4ndnis in Maschinen","funder_award_id":"442218748","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7608623061","display_name":null,"funder_award_id":"202006290013","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402111518.pdf","grobid_xml":"https://content.openalex.org/works/W4402111518.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2064370490","https://openalex.org/W3166813893","https://openalex.org/W2910013580","https://openalex.org/W2391900574","https://openalex.org/W3200958703","https://openalex.org/W1990078780","https://openalex.org/W3108667266","https://openalex.org/W2376619307"],"abstract_inverted_index":{"Contrastive":[0],"language-audio":[1],"pretraining":[2],"(CLAP)":[3],"has":[4],"recently":[5],"emerged":[6],"as":[7],"a":[8,22,35,43,81,106,113,124],"method":[9],"for":[10,50,56,76,91,104,116],"making":[11],"audio":[12,32,58,72,93],"analysis":[13],"more":[14],"generalisable.Specifically,":[15],"CLAP-style":[16,107],"models":[17,33,89],"are":[18,54,67,145],"able":[19],"to":[20,110,134],"'answer'":[21],"diverse":[23],"set":[24,37,45,125],"of":[25,31,38,46,126,138],"language":[26],"queries,":[27],"extending":[28],"the":[29,83,97,136],"capabilities":[30],"beyond":[34],"closed":[36],"labels.However,":[39],"CLAP":[40,88],"relies":[41,85],"on":[42,86,123],"large":[44],"(audio,":[47],"query)":[48],"pairs":[49],"pretraining.While":[51],"such":[52],"sets":[53],"available":[55,147],"general":[57,92],"tasks,":[59,129],"like":[60],"captioning":[61],"or":[62],"sound":[63],"event":[64],"detection,":[65],"there":[66],"no":[68],"datasets":[69],"with":[70,94],"matched":[71],"and":[73,143],"text":[74],"queries":[75],"computational":[77,127],"paralinguistic":[78,128],"(CP)":[79],"tasks.As":[80],"result,":[82],"community":[84],"generic":[87],"trained":[90],"limited":[95],"success.In":[96],"present":[98],"study,":[99],"we":[100],"explore":[101],"training":[102],"considerations":[103],"ParaCLAP,":[105],"model":[108],"suited":[109],"CP,":[111],"including":[112],"novel":[114],"process":[115],"creating":[117],"audio-language":[118],"queries.We":[119],"demonstrate":[120],"its":[121],"effectiveness":[122],"where":[130],"it":[131],"is":[132],"shown":[133],"surpass":[135],"performance":[137],"open-source":[139],"state-of-theart":[140],"models.Our":[141],"code":[142],"resources":[144],"publicly":[146],"at:":[148],"https://github.com/KeiKinn/ParaCLAP":[149]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
