{"id":"https://openalex.org/W4296068789","doi":"https://doi.org/10.21437/interspeech.2022-271","title":"Independence-based Joint Dereverberation and Separation with Neural Source Model","display_name":"Independence-based Joint Dereverberation and Separation with Neural Source Model","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296068789","doi":"https://doi.org/10.21437/interspeech.2022-271"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-271","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-271","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","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/A5079146015","display_name":"Kohei Saijo","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]},{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kohei Saijo","raw_affiliation_strings":["LINE Corporation, Japan","Waseda University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corporation, Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020401831","display_name":"Robin Scheibler","orcid":"https://orcid.org/0000-0002-5205-8365"},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Robin Scheibler","raw_affiliation_strings":["LINE Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corporation, Japan","institution_ids":["https://openalex.org/I4210096607"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079146015"],"corresponding_institution_ids":["https://openalex.org/I150744194","https://openalex.org/I4210096607"],"apc_list":null,"apc_paid":null,"fwci":0.7383,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69082657,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"236","last_page":"240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9995999932289124,"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":0.9973000288009644,"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/source-separation","display_name":"Source separation","score":0.7729242444038391},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7210581302642822},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.7086855173110962},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.6530143022537231},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5968033671379089},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5964556336402893},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35894906520843506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34746986627578735},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16382941603660583},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12586158514022827},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0958196222782135},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09277224540710449},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.059100598096847534}],"concepts":[{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7729242444038391},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7210581302642822},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.7086855173110962},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.6530143022537231},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5968033671379089},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5964556336402893},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35894906520843506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34746986627578735},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16382941603660583},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12586158514022827},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0958196222782135},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09277224540710449},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.059100598096847534},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-271","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-271","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W71081281","https://openalex.org/W1522301498","https://openalex.org/W1543386260","https://openalex.org/W1552314771","https://openalex.org/W1845880232","https://openalex.org/W2072548008","https://openalex.org/W2099741732","https://openalex.org/W2114461480","https://openalex.org/W2125114513","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2164502538","https://openalex.org/W2221409856","https://openalex.org/W2289394825","https://openalex.org/W2398042854","https://openalex.org/W2408744528","https://openalex.org/W2412956798","https://openalex.org/W2460742184","https://openalex.org/W2567070169","https://openalex.org/W2954049404","https://openalex.org/W2954695182","https://openalex.org/W2962780374","https://openalex.org/W2962935966","https://openalex.org/W2987027330","https://openalex.org/W3015678657","https://openalex.org/W3016232124","https://openalex.org/W3086154751","https://openalex.org/W3130736950","https://openalex.org/W3163217847","https://openalex.org/W3163257865","https://openalex.org/W3163391314","https://openalex.org/W3163842642","https://openalex.org/W3171278394","https://openalex.org/W4295312788"],"related_works":["https://openalex.org/W1509813908","https://openalex.org/W2031820693","https://openalex.org/W3024816962","https://openalex.org/W973023320","https://openalex.org/W1910172735","https://openalex.org/W2118307209","https://openalex.org/W2107364365","https://openalex.org/W2539388437","https://openalex.org/W2107688514","https://openalex.org/W2137288760"],"abstract_inverted_index":{"We":[0],"propose":[1],"an":[2,28,43],"independence-based":[3],"joint":[4,35],"dereverberation":[5,36],"and":[6,37,94],"separation":[7,54],"method":[8,58,82],"with":[9,46,65,102],"a":[10,15,47,103],"neural":[11,16],"source":[12,24],"model.We":[13],"introduce":[14],"network":[17,39],"in":[18,42,62,84,87],"the":[19,52,110,121,124],"framework":[20],"of":[21,30,74,89,106],"time-decorrelation":[22],"iterative":[23],"steering,":[25],"which":[26],"is":[27,40],"extension":[29],"independent":[31],"vector":[32],"analysis":[33],"to":[34],"separation.The":[38],"trained":[41,112],"end-to-end":[44],"manner":[45],"permutation":[48],"invariant":[49],"loss":[50],"on":[51,113,123],"time-domain":[53],"output":[55],"signals.Our":[56],"proposed":[57],"can":[59],"be":[60],"applied":[61],"any":[63,117],"situation":[64],"at":[66],"least":[67],"as":[68,71],"many":[69],"microphones":[70],"sources,":[72],"regardless":[73],"their":[75],"number.In":[76],"experiments,":[77],"we":[78],"demonstrate":[79],"that":[80],"our":[81],"results":[83],"high":[85],"performance":[86],"terms":[88],"both":[90],"speech":[91],"quality":[92],"metrics":[93],"word":[95],"error":[96],"rate":[97],"(WER),":[98],"even":[99],"for":[100],"mixtures":[101],"different":[104],"number":[105],"speakers":[107],"than":[108],"training.Furthermore,":[109],"model,":[111],"synthetic":[114],"mixtures,":[115],"without":[116],"modifications,":[118],"greatly":[119],"reduces":[120],"WER":[122],"recorded":[125],"dataset":[126],"LibriCSS.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}