{"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":{"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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-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/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'Information (LTCI), Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France"],"affiliations":[{"raw_affiliation_string":"Laboratoire de Traitement et Communication de l'Information (LTCI), Télécom 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/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'Information (LTCI), Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France","Meta Reality Labs (United States)"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs (United States)","institution_ids":["https://openalex.org/I4210128585"]},{"raw_affiliation_string":"Laboratoire de Traitement et Communication de l'Information (LTCI), Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France","institution_ids":["https://openalex.org/I4210165912"]}]},{"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/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'Information (LTCI), Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France"],"affiliations":[{"raw_affiliation_string":"Laboratoire de Traitement et Communication de l'Information (LTCI), Télécom 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/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'Information (LTCI), Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France"],"affiliations":[{"raw_affiliation_string":"Laboratoire de Traitement et Communication de l'Information (LTCI), Télécom 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/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'Information (LTCI), Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France"],"affiliations":[{"raw_affiliation_string":"Laboratoire de Traitement et Communication de l'Information (LTCI), Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France","institution_ids":["https://openalex.org/I4210165912"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.996,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":5,"citation_normalized_percentile":{"value":0.999798,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"1392","last_page":"1405"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9999,"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":0.9999,"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":0.9921,"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":0.9893,"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":0.89555365},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative Matrix Factorization","score":0.73691547}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.89555365},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7442198},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.73691547},{"id":"https://openalex.org/C122783720","wikidata":"https://www.wikidata.org/wiki/Q183065","display_name":"Interpreter","level":2,"score":0.58253974},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.5493384},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5132623},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.49509206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48663315},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.43050504},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3987496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37689814},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35006917},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.086186826},{"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":4,"locations":[{"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":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://hal.science/hal-04539879","pdf_url":"https://hal.science/hal-04539879/document","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://hal.science/hal-04539879/file/L2I_TASLP-4.pdf","pdf_url":"https://hal.science/hal-04539879/file/L2I_TASLP-4.pdf","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2305.07132","pdf_url":"https://arxiv.org/pdf/2305.07132","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://hal.science/hal-04539879","pdf_url":"https://hal.science/hal-04539879/document","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.66,"display_name":"Peace, justice, and strong institutions"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":46,"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"],"related_works":["https://openalex.org/W4390394189","https://openalex.org/W2972997031","https://openalex.org/W2792706544","https://openalex.org/W2539013788","https://openalex.org/W2156699640","https://openalex.org/W2146544734","https://openalex.org/W2127243424","https://openalex.org/W2045265907","https://openalex.org/W2037504162","https://openalex.org/W1568451138"],"abstract_inverted_index":{"This":[0,45],"paper":[1],"tackles":[2],"two":[3],"major":[4],"problem":[5],"settings":[6],"for":[7,42,118,136],"interpretability":[8],"of":[9,29,34,87,94,112,130],"audio":[10,36,138],"processing":[11],"networks,":[12],"post-hoc":[15],"and":[16,139],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">by-design":[19],"interpretation.":[20],"For":[21],"post-hoc":[22],"interpretation,":[23],"we":[24,60],"aim":[25],"to":[26,48,78,103],"interpret":[27],"decisions":[28],"a":[30,62,80,88,95,119,128],"network":[31],"in":[32],"terms":[33],"high-level":[35],"objects":[37],"that":[38,66,108],"are":[39],"also":[40],"listenable":[41],"the":[43,113],"end-user.":[44],"is":[46,76],"extended":[47],"present":[49],"an":[50,74],"inherently":[51],"interpretable":[52],"model":[53],"with":[54],"high":[55],"performance.":[56],"To":[57],"this":[58],"end,":[59],"propose":[61],"novel":[63],"interpreter":[64,75],"design":[65],"incorporates":[67],"non-negative":[68],"matrix":[69],"factorization":[70],"(NMF).":[71],"In":[72],"particular,":[73],"trained":[77],"generate":[79,104],"regularized":[81],"intermediate":[82],"embedding":[83],"from":[84],"hidden":[85],"layers":[86],"_target":[89],"network,":[90],"learnt":[91],"as":[92],"time-activations":[93],"pre-learnt":[96],"NMF":[97],"dictionary.":[98],"Our":[99],"methodology":[100],"allows":[101],"us":[102],"intuitive":[105],"audio-based":[106],"interpretations":[107],"explicitly":[109],"enhance":[110],"parts":[111],"input":[114],"signal":[115],"most":[116],"relevant":[117],"network's":[120],"decision.":[121],"We":[122],"demonstrate":[123],"our":[124],"method's":[125],"applicability":[126],"on":[127],"variety":[129],"classification":[131],"tasks,":[132],"including":[133],"multi-label":[134],"data":[135],"real-world":[137],"music.":[140]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4391164243","counts_by_year":[{"year":2024,"cited_by_count":5}],"updated_date":"2025-01-03T10:17:48.055560","created_date":"2024-01-25"}
  NODES