{"id":"https://openalex.org/W7126446111","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.154","title":"Establishing degrees of closeness between audio recordings along different dimensions using large-scale cross-lingual models","display_name":"Establishing degrees of closeness between audio recordings along different dimensions using large-scale cross-lingual models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126446111","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.154"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.154","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.154","pdf_url":"https://aclanthology.org/2024.findings-eacl.154.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.154.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Maxime Fily","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maxime Fily","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Guillaume Wisniewski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guillaume Wisniewski","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Severine Guillaume","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Severine Guillaume","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Gilles Adda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gilles Adda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Alexis Michaud","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexis Michaud","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43982193,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2332","last_page":"2341"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.71670001745224,"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":0.71670001745224,"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":0.11320000141859055,"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":0.05299999937415123,"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/closeness","display_name":"Closeness","score":0.45559999346733093},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.299699991941452},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2883000075817108},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.28119999170303345},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.27070000767707825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5263000130653381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4724000096321106},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36970001459121704},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.299699991941452},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28760001063346863},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.154","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.154","pdf_url":"https://aclanthology.org/2024.findings-eacl.154.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.154","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.154","pdf_url":"https://aclanthology.org/2024.findings-eacl.154.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4796545207500458,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1702322194","display_name":"Probing Neural Representations for Typological Signal","funder_award_id":"ANR-23-CE38-0003","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126446111.pdf","grobid_xml":"https://content.openalex.org/works/W7126446111.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"the":[1,28,50,56,61,93,104],"highly":[2],"constrained":[3],"context":[4],"of":[5,13,23,52],"lowresource":[6],"language":[7],"studies,":[8],"we":[9],"explore":[10],"vector":[11,112],"representations":[12,62,94],"speech":[14,67],"from":[15,96],"a":[16,32,65,70],"pretrained":[17],"model":[18,68],"to":[19,27,46,122],"determine":[20,59],"their":[21],"level":[22],"abstraction":[24],"with":[25,42,98],"regard":[26],"audio":[29,40,108],"signal.We":[30],"propose":[31],"new":[33,132],"unsupervised":[34],"method":[35,126],"using":[36],"ABX":[37],"tests":[38,58],"on":[39,49,77,82,87,138],"recordings":[41,97],"carefully":[43],"curated":[44],"metadata":[45],"shed":[47],"light":[48],"type":[51],"information":[53],"present":[54],"in":[55,110],"representations.ABX":[57],"whether":[60],"computed":[63],"by":[64],"multilingual":[66],"encode":[69],"given":[71],"characteristic.Three":[72],"experiments":[73],"are":[74,120],"devised:":[75],"one":[76,81,86,111],"room":[78],"acoustics":[79],"aspects,":[80],"linguistic":[83],"genre,":[84],"and":[85],"phonetic":[88],"aspects.The":[89],"results":[90],"confirm":[91],"that":[92],"extracted":[95],"different":[99],"linguistic/extralinguistic":[100],"characteristics":[101],"differ":[102],"along":[103],"same":[105],"lines.Embedding":[106],"more":[107],"signal":[109],"better":[113,121],"discriminates":[114],"extra-linguistic":[115],"characteristics,":[116],"whereas":[117],"shorter":[118],"snippets":[119],"distinguish":[123],"segmental":[124],"information.The":[125],"is":[127],"fully":[128],"unsupervised,":[129],"potentially":[130],"opening":[131],"research":[133],"avenues":[134],"for":[135],"comparative":[136],"work":[137],"under-documented":[139],"languages.":[140]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}