{"id":"https://openalex.org/W4415432741","doi":"https://doi.org/10.21437/interspeech.2025-2784","title":"SepVAC: Multitask Learning of Speaker Separation, Speaker Localization, Microphone Array Localization, and Room Acoustic Parameter Estimation in Various Acoustic Conditions","display_name":"SepVAC: Multitask Learning of Speaker Separation, Speaker Localization, Microphone Array Localization, and Room Acoustic Parameter Estimation in Various Acoustic Conditions","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432741","doi":"https://doi.org/10.21437/interspeech.2025-2784"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-2784","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100939015","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018038856","display_name":"Roland Hartanto","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Roland Hartanto","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045461854","display_name":"Sakriani Sakti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081629487","display_name":"Koichi Shinoda","orcid":"https://orcid.org/0000-0003-1095-3203"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koichi Shinoda","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018038856"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36961999,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2480","last_page":"2484"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9923999905586243,"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":0.9923999905586243,"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":0.9714000225067139,"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/microphone","display_name":"Microphone","score":0.592199981212616},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.531000018119812},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.424699991941452},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.29260000586509705},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2720000147819519},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2689000070095062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6233000159263611},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.592199981212616},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.554099977016449},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.531000018119812},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.47049999237060547},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.424699991941452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42289999127388},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.29260000586509705},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.2630000114440918},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25760000944137573}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-2784","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:00897:0006991958","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100939015","pdf_url":null,"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,"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":"Proc. Interspeech 2025","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:00897:0006991958","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100939015","pdf_url":null,"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,"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":"Proc. Interspeech 2025","raw_type":"conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3],"multitask":[4],"learning":[5,62],"method":[6,42],"for":[7],"speech":[8,12,57],"separation,":[9],"that":[10,28],"Separates":[11],"and":[13,39,49],"estimates":[14,44],"the":[15,25,34,65,77],"recording":[16],"conditions":[17],"in":[18,84],"Various":[19],"Acoustic":[20],"Conditions":[21],"(SepVAC)":[22],"jointly.":[23],"Unlike":[24],"previous":[26],"methods":[27],"aim":[29],"to":[30,53,63],"achieve":[31],"robustness":[32],"against":[33],"uncertainty":[35],"caused":[36],"by":[37,81],"noise":[38],"reverberation,":[40],"this":[41],"explicitly":[43],"speaker":[45],"&":[46],"microphone":[47],"location":[48],"room":[50],"acoustic":[51],"parameters":[52,67],"disambiguate":[54],"them":[55],"from":[56],"features.":[58],"We":[59],"introduce":[60],"curriculum":[61],"learn":[64],"model":[66],"stably.":[68],"In":[69],"our":[70],"evaluation":[71],"using":[72],"SMS-WSJ-Plus":[73],"dataset,":[74],"it":[75],"outperforms":[76],"state-of-the-art":[78],"SpatialNet":[79],"baseline":[80],"0.67":[82],"points":[83],"word":[85],"error":[86],"rate":[87],"(WER).":[88]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-24T00:00:00"}