{"id":"https://openalex.org/W6983604458","doi":null,"title":"Multitask Training of Multi-channel Speaker Separation and Room Acoustic Parameter Estimation","display_name":"Multitask Training of Multi-channel Speaker Separation and Room Acoustic Parameter Estimation","publication_year":2025,"publication_date":"2025-03-01","ids":{"openalex":"https://openalex.org/W6983604458"},"language":"en","primary_location":{"id":"pmh:oai:irdb.nii.ac.jp:00894:0007548053","doi":null,"is_oa":true,"landing_page_url":"https://isct.repo.nii.ac.jp/records/2003365","pdf_url":"https://isct.repo.nii.ac.jp/record/2003365/files/1753766056888.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"\u65e5\u672c\u97f3\u97ff\u5b66\u4f1a\u7b2c153\u56de(2025\u5e74\u6625\u5b63)\u7814\u7a76\u767a\u8868\u4f1a\u8b1b\u6f14\u8ad6\u6587\u96c6","raw_type":"conference paper"},"parent_works":[],"lineage":["https://openalex.org/W6983604458"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://isct.repo.nii.ac.jp/record/2003365/files/1753766056888.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hartanto, Roland","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":"JP","type":"education","lineage":["https://openalex.org/I4400009020"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hartanto, Roland","raw_affiliation_strings":["(Science Tokyo) , Sakriani Sakti (NAIST) ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"(Science Tokyo) , Sakriani Sakti (NAIST) ,","institution_ids":["https://openalex.org/I4400009020","https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hartanto, Roland","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":"JP","type":"education","lineage":["https://openalex.org/I4400009020"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hartanto, Roland","raw_affiliation_strings":["(Science Tokyo) , Sakriani Sakti (NAIST) ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"(Science Tokyo) , Sakriani Sakti (NAIST) ,","institution_ids":["https://openalex.org/I4400009020","https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045461854","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963","observed_orcids":["https://orcid.org/0000-0001-5509-8963"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sakti, Sakriani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"\u7be0\u7530, \u6d69\u4e00","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u7be0\u7530, \u6d69\u4e00","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Shinoda, Koichi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":"JP","type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinoda, Koichi","raw_affiliation_strings":["(Science Tokyo)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"(Science Tokyo)","institution_ids":["https://openalex.org/I4400009020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"233","last_page":"234"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9937000274658203,"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":0.9937000274658203,"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":0.00559999980032444,"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/T11309","display_name":"Music and Audio Processing","score":0.0003000000142492354,"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/multi-channel-speech-separation","display_name":"multi-channel speech separation","score":0.8019999861717224},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.953000009059906},{"id":"https://openalex.org/keywords/permutation-invariant-training","display_name":"permutation invariant training","score":0.9139999747276306},{"id":"https://openalex.org/keywords/doa-estimation","display_name":"direction of arrival estimation","score":0.7720000147819519},{"id":"https://openalex.org/keywords/speaker-localization","display_name":"speaker localization","score":0.9399999976158142},{"id":"https://openalex.org/keywords/reverberation","display_name":"reverberation","score":0.7799999713897705},{"id":"https://openalex.org/keywords/overlapping-speech","display_name":"overlapping speech","score":0.5649999976158142},{"id":"https://openalex.org/keywords/room-size","display_name":"room size","score":0.40400001406669617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7111999988555908},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.708899974822998},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6851999759674072},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.632099986076355},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6119999885559082},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6043999791145325},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5881999731063843},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.52920001745224},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4147000014781952},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3799000084400177},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.34150001406669617},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.33239999413490295},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.288100004196167},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C108250783","wikidata":"https://www.wikidata.org/wiki/Q4674710","display_name":"Acoustic space","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2800000011920929},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C178432105","wikidata":"https://www.wikidata.org/wiki/Q2182127","display_name":"Room acoustics","level":3,"score":0.2621999979019165}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:irdb.nii.ac.jp:00894:0007548053","doi":null,"is_oa":true,"landing_page_url":"https://isct.repo.nii.ac.jp/records/2003365","pdf_url":"https://isct.repo.nii.ac.jp/record/2003365/files/1753766056888.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"\u65e5\u672c\u97f3\u97ff\u5b66\u4f1a\u7b2c153\u56de(2025\u5e74\u6625\u5b63)\u7814\u7a76\u767a\u8868\u4f1a\u8b1b\u6f14\u8ad6\u6587\u96c6","raw_type":"conference paper"},{"id":"pmh:oai:irdb.nii.ac.jp:00897:0006861246","doi":null,"is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100934314","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100934314/ATD100000413/ASJ2025_Spring_Roland.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"\u65e5\u672c\u97f3\u97ff\u5b66\u4f1a\u7b2c153\u56de(2025\u5e74\u6625\u5b63)\u7814\u7a76\u767a\u8868\u4f1a\u8b1b\u6f14\u8ad6\u6587\u96c6","raw_type":"conference paper"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50735799","doi":null,"is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100934314","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:00894:0007548053","doi":null,"is_oa":true,"landing_page_url":"https://isct.repo.nii.ac.jp/records/2003365","pdf_url":"https://isct.repo.nii.ac.jp/record/2003365/files/1753766056888.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"\u65e5\u672c\u97f3\u97ff\u5b66\u4f1a\u7b2c153\u56de(2025\u5e74\u6625\u5b63)\u7814\u7a76\u767a\u8868\u4f1a\u8b1b\u6f14\u8ad6\u6587\u96c6","raw_type":"conference paper"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6983604458.pdf","grobid_xml":"https://content.openalex.org/works/W6983604458.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7002121965","https://openalex.org/W4415432741","https://openalex.org/W4375869047","https://openalex.org/W3027465796","https://openalex.org/W2786105640","https://openalex.org/W7205395212","https://openalex.org/W2939360348","https://openalex.org/W2952482988","https://openalex.org/W4402111248","https://openalex.org/W2888954542"],"abstract_inverted_index":{"Speaker":[0],"separation":[1,28,44,59,62,114,161,180,215],"focuses":[2],"on":[3,97],"extracting":[4],"individual":[5],"speech":[6,10,20,43,58,95,206],"signals":[7],"from":[8,207],"a":[9],"mixture.":[11],"It":[12],"is":[13,53],"applied":[14],"for":[15,41,56,100],"single":[16],"and":[17,31,103,115,151,170],"multi-channel":[18,42],"front-end":[19],"processing":[21],"to":[22,92,127,178,196],"deal":[23],"with":[24,163],"overlapping":[25],"speech.":[26],"Multichannel":[27],"leverages":[29,86],"spectral":[30],"spatial":[32],"information":[33,76,177],"of":[34,90,112,219],"speakers,":[35],"improving":[36,119,201],"separation.":[37,80,121,202],"Deep":[38],"learning":[39,111,158,192],"methods":[40],"have":[45],"been":[46],"widely":[47],"explored.":[48],"Permutation":[49],"Invariant":[50],"Training":[51,84],"(PIT)":[52],"an":[54],"approach":[55],"training":[57],"models,":[60],"minimizing":[61],"loss":[63,101],"across":[64],"all":[65],"possible":[66],"output-target":[67],"pair":[68],"permutations.":[69],"Other":[70],"studies":[71],"show":[72],"that":[73],"using":[74],"location":[75],"can":[77,137],"help":[78],"improve":[79,179],"For":[81],"example,":[82],"Location-Based":[83],"(LBT)":[85],"the":[87,120,159,217],"direction-of-arrival":[88],"(DoA)":[89],"speakers":[91],"organize":[93],"target":[94],"based":[96],"their":[98],"DoA":[99,116],"computation":[102],"performs":[104,109],"better":[105],"than":[106],"PIT.":[107],"MSDET":[108],"multitask":[110],"speaker":[113,123,152,160,168],"estimation,":[117,167],"further":[118],"However,":[122],"locations":[124],"are":[125],"insufficient":[126],"handle":[128],"various":[129,182],"acoustic":[130,139,183,199,209,221],"conditions.":[131,184],"In":[132],"real":[133],"environments,":[134],"many":[135],"parameters":[136,166],"affect":[138],"conditions,":[140],"such":[141],"as":[142],"room":[143,164,175,189,198,208,220],"size,":[144],"wall":[145],"surface":[146],"materials,":[147],"microphone":[148,171],"array":[149,172],"locations,":[150],"locations.":[153],"This":[154],"work":[155],"proposes":[156],"simultaneously":[157],"task":[162],"acoustics":[165,176],"localization,":[169,173],"exploiting":[174],"in":[181],"Separation":[185],"models":[186],"implicitly":[187],"learn":[188,197],"acoustics.":[190],"Multitask":[191],"allows":[193],"explicit":[194],"supervision":[195],"parameters,":[200],"Our":[203],"method":[204],"separates":[205],"features,":[210],"capturing":[211],"reverberation":[212],"information.":[213],"Better":[214],"improves":[216],"estimation":[218],"parameters.":[222]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2025-10-10T00:00:00"}