{"id":"https://openalex.org/W4391164243","doi":"https://doi.org/10.1109/taslp.2024.3358049","title":"Tackling Interpretability in Audio Classification Networks With Non-negative Matrix Factorization","display_name":"Tackling Interpretability in Audio Classification Networks With Non-negative Matrix Factorization","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391164243","doi":"https://doi.org/10.1109/taslp.2024.3358049"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3358049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3358049","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04539879/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049601339","display_name":"Jayneel Parekh","orcid":"https://orcid.org/0009-0008-4762-6998"},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jayneel Parekh","raw_affiliation_strings":["Laboratoire de Traitement et Communication de l&#x0027;Information (LTCI), T&#x00E9;l&#x00E9;com Paris, Institut Polytechnique de Paris, Palaiseau, France"],"raw_orcid":"https://orcid.org/0009-0008-4762-6998","affiliations":[{"raw_affiliation_string":"Laboratoire de Traitement et Communication de l&#x0027;Information (LTCI), T&#x00E9;l&#x00E9;com Paris, Institut Polytechnique de Paris, Palaiseau, France","institution_ids":["https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001145583","display_name":"Sanjeel Parekh","orcid":"https://orcid.org/0000-0002-2251-7436"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Sanjeel Parekh","raw_affiliation_strings":["Laboratoire de Traitement et Communication de l&#x0027;Information (LTCI), T&#x00E9;l&#x00E9;com Paris, Institut Polytechnique de Paris, Palaiseau, France","Meta Reality Labs (United States)"],"raw_orcid":"https://orcid.org/0000-0002-2251-7436","affiliations":[{"raw_affiliation_string":"Laboratoire de Traitement et Communication de l&#x0027;Information (LTCI), T&#x00E9;l&#x00E9;com Paris, Institut Polytechnique de Paris, Palaiseau, France","institution_ids":["https://openalex.org/I4210165912"]},{"raw_affiliation_string":"Meta Reality Labs (United States)","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041121259","display_name":"Pavlo Mozharovskyi","orcid":"https://orcid.org/0000-0002-1925-3337"},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pavlo Mozharovskyi","raw_affiliation_strings":["Laboratoire de Traitement et Communication de l&#x0027;Information (LTCI), T&#x00E9;l&#x00E9;com Paris, Institut Polytechnique de Paris, Palaiseau, France"],"raw_orcid":"https://orcid.org/0000-0002-1925-3337","affiliations":[{"raw_affiliation_string":"Laboratoire de Traitement et Communication de l&#x0027;Information (LTCI), T&#x00E9;l&#x00E9;com Paris, Institut Polytechnique de Paris, Palaiseau, France","institution_ids":["https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055423112","display_name":"Ga\u00ebl Richard","orcid":"https://orcid.org/0000-0002-4960-0010"},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ga\u00ebl Richard","raw_affiliation_strings":["Laboratoire de Traitement et Communication de l&#x0027;Information (LTCI), T&#x00E9;l&#x00E9;com Paris, Institut Polytechnique de Paris, Palaiseau, France"],"raw_orcid":"https://orcid.org/0000-0002-4960-0010","affiliations":[{"raw_affiliation_string":"Laboratoire de Traitement et Communication de l&#x0027;Information (LTCI), T&#x00E9;l&#x00E9;com Paris, Institut Polytechnique de Paris, Palaiseau, France","institution_ids":["https://openalex.org/I4210165912"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066766964","display_name":"Florence d\u2019Alch\u00e9\u2013Buc","orcid":"https://orcid.org/0000-0002-8353-0589"},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Florence d'Alch\u00e9-Buc","raw_affiliation_strings":["Laboratoire de Traitement et Communication de l&#x0027;Information (LTCI), T&#x00E9;l&#x00E9;com Paris, Institut Polytechnique de Paris, Palaiseau, France"],"raw_orcid":"https://orcid.org/0000-0002-8353-0589","affiliations":[{"raw_affiliation_string":"Laboratoire de Traitement et Communication de l&#x0027;Information (LTCI), T&#x00E9;l&#x00E9;com Paris, Institut Polytechnique de Paris, Palaiseau, France","institution_ids":["https://openalex.org/I4210165912"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5518,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.90031727,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"1392","last_page":"1405"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10320","display_name":"Neural Networks and Applications","score":0.9921000003814697,"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":0.989300012588501,"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/interpretability","display_name":"Interpretability","score":0.8955536484718323},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7442197799682617},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.7369154691696167},{"id":"https://openalex.org/keywords/interpreter","display_name":"Interpreter","score":0.5825397372245789},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.5493384003639221},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5132622718811035},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4950920641422272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48663315176963806},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.43050503730773926},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39874958992004395},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3768981397151947},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35006916522979736},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08618682622909546}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8955536484718323},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7442197799682617},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.7369154691696167},{"id":"https://openalex.org/C122783720","wikidata":"https://www.wikidata.org/wiki/Q183065","display_name":"Interpreter","level":2,"score":0.5825397372245789},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.5493384003639221},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5132622718811035},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4950920641422272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48663315176963806},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.43050503730773926},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39874958992004395},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3768981397151947},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35006916522979736},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08618682622909546},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2024.3358049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3358049","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-04539879v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04539879","pdf_url":"https://hal.science/hal-04539879/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech and Language Processing, 2024, 32, pp.1392--1405. &#x27E8;10.1109/TASLP.2024.3358049&#x27E9;","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04539879v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04539879","pdf_url":"https://hal.science/hal-04539879/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech and Language Processing, 2024, 32, pp.1392--1405. &#x27E8;10.1109/TASLP.2024.3358049&#x27E9;","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6600000262260437}],"awards":[{"id":"https://openalex.org/G7746831961","display_name":"Leveraging Interpretable Machines for Performance Improvement and Decision","funder_award_id":"ANR-20-CE23-0028","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"},{"id":"https://openalex.org/F4320334537","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4391164243.pdf"},"referenced_works_count":73,"referenced_works":["https://openalex.org/W1537999046","https://openalex.org/W1555814299","https://openalex.org/W1964538581","https://openalex.org/W2015471578","https://openalex.org/W2052666245","https://openalex.org/W2071362688","https://openalex.org/W2106582496","https://openalex.org/W2116542188","https://openalex.org/W2145668323","https://openalex.org/W2158291955","https://openalex.org/W2332488709","https://openalex.org/W2516809705","https://openalex.org/W2593116425","https://openalex.org/W2619623002","https://openalex.org/W2657631929","https://openalex.org/W2765813195","https://openalex.org/W2783473931","https://openalex.org/W2872172641","https://openalex.org/W2917322567","https://openalex.org/W2945976633","https://openalex.org/W2952395326","https://openalex.org/W2959587146","https://openalex.org/W2962807820","https://openalex.org/W2962858109","https://openalex.org/W2962910554","https://openalex.org/W2963218389","https://openalex.org/W2964235918","https://openalex.org/W2969476445","https://openalex.org/W2972717745","https://openalex.org/W2979200397","https://openalex.org/W2997685131","https://openalex.org/W3083155260","https://openalex.org/W3085893206","https://openalex.org/W3090027309","https://openalex.org/W3137125108","https://openalex.org/W3146622378","https://openalex.org/W3206494219","https://openalex.org/W3214023923","https://openalex.org/W4246602265","https://openalex.org/W4256604311","https://openalex.org/W4283014787","https://openalex.org/W4287685631","https://openalex.org/W4287694183","https://openalex.org/W4287704719","https://openalex.org/W4293768783","https://openalex.org/W4293861706","https://openalex.org/W6631190155","https://openalex.org/W6680012447","https://openalex.org/W6712990308","https://openalex.org/W6737947904","https://openalex.org/W6739575509","https://openalex.org/W6746228475","https://openalex.org/W6747701563","https://openalex.org/W6750391026","https://openalex.org/W6752771859","https://openalex.org/W6752948792","https://openalex.org/W6753001334","https://openalex.org/W6753441104","https://openalex.org/W6756597712","https://openalex.org/W6764462969","https://openalex.org/W6764574124","https://openalex.org/W6766846328","https://openalex.org/W6769472369","https://openalex.org/W6772015689","https://openalex.org/W6775074090","https://openalex.org/W6781178991","https://openalex.org/W6781206141","https://openalex.org/W6781375186","https://openalex.org/W6783078499","https://openalex.org/W6784261405","https://openalex.org/W6796292747","https://openalex.org/W6811069199","https://openalex.org/W6843129683"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W2146544734"],"abstract_inverted_index":{"This":[0,37],"paper":[1],"tackles":[2],"two":[3],"major":[4],"problem":[5],"settings":[6],"for":[7,34,110,128],"interpretability":[8],"of":[9,21,26,79,86,104,122],"audio":[10,28,130],"processing":[11],"networks,post-hocandby-designinterpretation.":[12],"For":[13],"post-hoc":[14],"interpretation,":[15],"we":[16,52],"aim":[17],"to":[18,40,70,95],"interpret":[19],"decisions":[20],"a":[22,54,72,80,87,111,120],"network":[23],"in":[24],"terms":[25],"high-level":[27],"objects":[29],"that":[30,58,100],"are":[31],"also":[32],"listenable":[33],"the":[35,105],"end-user.":[36],"is":[38,68],"extended":[39],"present":[41],"an":[42,66],"inherently":[43],"interpretable":[44],"model":[45],"with":[46],"high":[47],"performance.":[48],"To":[49],"this":[50],"end,":[51],"propose":[53],"novel":[55],"interpreter":[56,67],"design":[57],"incorporates":[59],"non-negative":[60],"matrix":[61],"factorization":[62],"(NMF).":[63],"In":[64],"particular,":[65],"trained":[69],"generate":[71,96],"regularized":[73],"intermediate":[74],"embedding":[75],"from":[76],"hidden":[77],"layers":[78],"target":[81],"network,":[82],"learnt":[83],"as":[84],"time-activations":[85],"pre-learnt":[88],"NMF":[89],"dictionary.":[90],"Our":[91],"methodology":[92],"allows":[93],"us":[94],"intuitive":[97],"audio-based":[98],"interpretations":[99],"explicitly":[101],"enhance":[102],"parts":[103],"input":[106],"signal":[107],"most":[108],"relevant":[109],"network's":[112],"decision.":[113],"We":[114],"demonstrate":[115],"our":[116],"method's":[117],"applicability":[118],"on":[119],"variety":[121],"classification":[123],"tasks,":[124],"including":[125],"multi-label":[126],"data":[127],"real-world":[129],"and":[131],"music.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
