{"id":"https://openalex.org/W4391010932","doi":"https://doi.org/10.1109/icassp48485.2024.10446648","title":"An Explainable Proxy Model for Multilabel Audio Segmentation","display_name":"An Explainable Proxy Model for Multilabel Audio Segmentation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4391010932","doi":"https://doi.org/10.1109/icassp48485.2024.10446648"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446648","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://univ-lemans.hal.science/hal-04393946/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036816609","display_name":"Th\u00e9o Mariotte","orcid":"https://orcid.org/0000-0002-2108-101X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Th\u00e9o Mariotte","raw_affiliation_strings":["LIUM, Le Mans Université"],"affiliations":[{"raw_affiliation_string":"LIUM, Le Mans Université","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058087233","display_name":"Antonio Almud\u00e9var","orcid":"https://orcid.org/0000-0002-9407-1381"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Antonio Almud\u00e9var","raw_affiliation_strings":["University of Zaragoza,ViVoLab, Aragón Institute for Engineering Research (I3A)"],"affiliations":[{"raw_affiliation_string":"University of Zaragoza,ViVoLab, Aragón Institute for Engineering Research (I3A)","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028709353","display_name":"Marie Tahon","orcid":"https://orcid.org/0000-0002-6782-0332"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marie Tahon","raw_affiliation_strings":["LIUM, Le Mans Université"],"affiliations":[{"raw_affiliation_string":"LIUM, Le Mans Université","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101903408","display_name":"Alfonso Ortega","orcid":"https://orcid.org/0000-0002-3886-7748"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alfonso Ortega","raw_affiliation_strings":["University of Zaragoza,ViVoLab, Aragón Institute for Engineering Research (I3A)"],"affiliations":[{"raw_affiliation_string":"University of Zaragoza,ViVoLab, Aragón Institute for Engineering Research (I3A)","institution_ids":["https://openalex.org/I255234318"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036816609"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3452,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46775134,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"2","issue":null,"first_page":"531","last_page":"535"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9961000084877014,"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":0.9961000084877014,"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":0.9724000096321106,"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":0.788399338722229},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.7345854043960571},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5833475589752197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38441893458366394},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19488966464996338}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.788399338722229},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.7345854043960571},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5833475589752197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38441893458366394},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19488966464996338}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446648","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04393946v1","is_oa":true,"landing_page_url":"https://univ-lemans.hal.science/hal-04393946","pdf_url":"https://univ-lemans.hal.science/hal-04393946/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"International Conference on Acoustics Speech and Signal Processing, IEEE, Apr 2024, Seoul (Korea), France","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04393946v1","is_oa":true,"landing_page_url":"https://univ-lemans.hal.science/hal-04393946","pdf_url":"https://univ-lemans.hal.science/hal-04393946/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"International Conference on Acoustics Speech and Signal Processing, IEEE, Apr 2024, Seoul (Korea), France","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391010932.pdf"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1987426045","https://openalex.org/W2009876684","https://openalex.org/W2129120544","https://openalex.org/W2142171915","https://openalex.org/W2516809705","https://openalex.org/W2792764867","https://openalex.org/W2952003418","https://openalex.org/W2953763392","https://openalex.org/W2968951209","https://openalex.org/W2981728176","https://openalex.org/W3012971020","https://openalex.org/W3015780472","https://openalex.org/W3097148135","https://openalex.org/W3146622378","https://openalex.org/W3157070662","https://openalex.org/W3161656685","https://openalex.org/W3196595845","https://openalex.org/W3198482860","https://openalex.org/W3198827946","https://openalex.org/W3203575608","https://openalex.org/W3209984917","https://openalex.org/W4212774754","https://openalex.org/W4295365513","https://openalex.org/W4384831944","https://openalex.org/W4385291717","https://openalex.org/W4391164243","https://openalex.org/W6622801540","https://openalex.org/W6638523607","https://openalex.org/W6680012447","https://openalex.org/W6746228475","https://openalex.org/W6749825310","https://openalex.org/W6766369501","https://openalex.org/W6854926564"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Audio":[0],"signal":[1],"segmentation":[2,47,79],"is":[3,28],"a":[4,29],"key":[5],"task":[6],"for":[7,32,77,108],"automatic":[8],"audio":[9],"indexing.":[10],"It":[11],"consists":[12],"of":[13,17,34],"detecting":[14],"the":[15,21,67,74,78,81,93,104,109,117],"boundaries":[16],"class-homogeneous":[18],"segments":[19],"in":[20],"signal.":[22],"In":[23,39],"many":[24],"applications,":[25],"explainable":[26,45,100],"AI":[27],"vital":[30],"process":[31],"transparency":[33],"decision-making":[35],"with":[36],"machine":[37],"learning.":[38],"this":[40],"paper,":[41],"we":[42],"propose":[43],"an":[44],"multilabel":[46],"model":[48,97],"that":[49],"solves":[50],"speech":[51,60],"activity":[52],"(SAD),":[53],"music":[54],"(MD),":[55],"noise":[56],"(ND),":[57],"and":[58,122],"overlapped":[59],"detection":[61],"(OSD)":[62],"simultaneously.":[63],"This":[64],"proxy":[65],"uses":[66],"non-negative":[68],"matrix":[69],"factorization":[70],"(NMF)":[71],"to":[72,80],"map":[73],"embeddings":[75],"used":[76,107],"frequency":[82,105],"domain.":[83],"Experiments":[84],"conducted":[85],"on":[86],"two":[87],"datasets":[88],"show":[89],"similar":[90],"performances":[91],"as":[92],"pre-trained":[94],"black":[95],"box":[96],"while":[98],"strong":[99],"features":[101],"arise.":[102],"Specifically,":[103],"bins":[106],"decision":[110],"can":[111],"be":[112],"easily":[113],"identified":[114],"at":[115],"both":[116],"segment":[118],"level":[119,124],"(local":[120],"explanations)":[121],"global":[123],"(class":[125],"prototypes).":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}