{"id":"https://openalex.org/W4408353394","doi":"https://doi.org/10.1109/icassp49660.2025.10888528","title":"Multiple Choice Learning for Efficient Speech Separation with Many Speakers","display_name":"Multiple Choice Learning for Efficient Speech Separation with Many Speakers","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353394","doi":"https://doi.org/10.1109/icassp49660.2025.10888528"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089399270","display_name":"David Perera","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"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":true,"raw_author_name":"David Perera","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, Télécom Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, Télécom Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I4210145102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114989744","display_name":"Fran\u00e7ois Derrida","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"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":"Fran\u00e7ois Derrida","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, Télécom Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, Télécom Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I4210145102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036816609","display_name":"Th\u00e9o Mariotte","orcid":"https://orcid.org/0000-0002-2108-101X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Th\u00e9o Mariotte","raw_affiliation_strings":["Le Mans Université,LIUM,Le Mans,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Le Mans Université,LIUM,Le Mans,France","institution_ids":[]}]},{"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/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"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":["Institut Polytechnique de Paris,LTCI, Télécom Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, Télécom Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I4210145102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060031161","display_name":"Slim Essid","orcid":"https://orcid.org/0000-0002-0028-327X"},"institutions":[{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"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":"Slim Essid","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, Télécom Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, Télécom Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I4210145102"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5089399270"],"corresponding_institution_ids":["https://openalex.org/I4210145102","https://openalex.org/I4210165912"],"apc_list":null,"apc_paid":null,"fwci":1.2189,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.7481387,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.9847999811172485,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9750000238418579,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7651205062866211},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.618009626865387},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6003748178482056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3439311385154724},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13714569807052612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7651205062866211},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.618009626865387},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6003748178482056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3439311385154724},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13714569807052612}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04981264v1","is_oa":false,"landing_page_url":"https://telecom-paris.hal.science/hal-04981264","pdf_url":null,"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":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2025, Hyderabad, India. ⟨10.1109/ICASSP49660.2025.10888528⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1790748249","https://openalex.org/W1982928063","https://openalex.org/W2026573146","https://openalex.org/W2029715674","https://openalex.org/W2051727797","https://openalex.org/W2144763279","https://openalex.org/W2149342630","https://openalex.org/W2150593711","https://openalex.org/W2164098335","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2557519264","https://openalex.org/W2558649592","https://openalex.org/W2952218014","https://openalex.org/W2952752702","https://openalex.org/W2962866211","https://openalex.org/W2964058413","https://openalex.org/W2998657200","https://openalex.org/W3094380169","https://openalex.org/W3095212884","https://openalex.org/W3116293816","https://openalex.org/W3151851237","https://openalex.org/W3197823486","https://openalex.org/W4289665794","https://openalex.org/W4375869348","https://openalex.org/W4385756463","https://openalex.org/W4387938956","https://openalex.org/W4390660238","https://openalex.org/W4392903841","https://openalex.org/W6681912825","https://openalex.org/W6682962330","https://openalex.org/W6720019270","https://openalex.org/W6768815455","https://openalex.org/W6774995033","https://openalex.org/W6777776875","https://openalex.org/W6784764134","https://openalex.org/W6838415197","https://openalex.org/W6858581201","https://openalex.org/W6873901268"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2071676784","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Training":[0,36],"speech":[1,105],"separation":[2,106],"models":[3],"in":[4,107],"the":[5,13,17,21,45,63,72,82,108],"supervised":[6],"setting":[7],"raises":[8],"a":[9,85,97],"permutation":[10],"problem:":[11],"finding":[12],"best":[14],"assignation":[15],"between":[16],"model":[18],"predictions":[19],"and":[20,66],"ground":[22],"truth":[23],"separated":[24],"signals.":[25],"This":[26,80],"inherently":[27],"ambiguous":[28,57],"task":[29],"is":[30],"customarily":[31],"solved":[32],"using":[33,44],"Permutation":[34],"Invariant":[35],"(PIT).":[37],"In":[38],"this":[39],"article,":[40],"we":[41],"instead":[42],"consider":[43],"Multiple":[46],"Choice":[47],"Learning":[48],"(MCL)":[49],"framework,":[50],"which":[51],"was":[52],"originally":[53],"introduced":[54],"to":[55,84,95,103],"tackle":[56,104],"tasks.":[58],"We":[59],"demonstrate":[60],"experimentally":[61],"on":[62],"popular":[64],"WSJ0-mix":[65],"LibriMix":[67],"benchmarks":[68],"that":[69],"MCL":[70,90],"matches":[71],"performances":[73],"of":[74,100],"PIT,":[75],"while":[76],"being":[77],"computationally":[78],"advantageous.":[79],"opens":[81],"door":[83],"promising":[86],"research":[87],"direction,":[88],"as":[89],"can":[91],"be":[92],"naturally":[93],"extended":[94],"handle":[96],"variable":[98],"number":[99],"speakers,":[101],"or":[102],"unsupervised":[109],"setting.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}