{"id":"https://openalex.org/W4402111248","doi":"https://doi.org/10.21437/interspeech.2024-2537","title":"MSDET: Multitask Speaker Separation and Direction-of-Arrival Estimation Training","display_name":"MSDET: Multitask Speaker Separation and Direction-of-Arrival Estimation Training","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111248","doi":"https://doi.org/10.21437/interspeech.2024-2537"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-2537","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-2537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"conference-paper","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=CTT100927130","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":false,"raw_author_name":"Roland Hartanto","raw_affiliation_strings":[],"raw_orcid":null,"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":[],"raw_orcid":null,"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":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2170","last_page":"2174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9965000152587891,"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":0.9965000152587891,"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":0.9951000213623047,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.933899998664856,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7421650290489197},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6540016531944275},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6489759683609009},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5617051124572754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49314063787460327},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4900761842727661},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.46586063504219055},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.4530888795852661},{"id":"https://openalex.org/keywords/multilateration","display_name":"Multilateration","score":0.4281266927719116},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33203834295272827},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.26001352071762085},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12097880244255066},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08854806423187256},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08088594675064087},{"id":"https://openalex.org/keywords/azimuth","display_name":"Azimuth","score":0.07440763711929321}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7421650290489197},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6540016531944275},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6489759683609009},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5617051124572754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49314063787460327},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4900761842727661},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.46586063504219055},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.4530888795852661},{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.4281266927719116},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33203834295272827},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26001352071762085},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12097880244255066},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08854806423187256},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08088594675064087},{"id":"https://openalex.org/C159737794","wikidata":"https://www.wikidata.org/wiki/Q124274","display_name":"Azimuth","level":2,"score":0.07440763711929321},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2024-2537","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-2537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:00897:0006496961","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100927130","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 2024","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:00897:0006496961","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100927130","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 2024","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":["https://openalex.org/W2380293945","https://openalex.org/W1500522817","https://openalex.org/W1974812937","https://openalex.org/W3095239554","https://openalex.org/W3212409750","https://openalex.org/W4387088887","https://openalex.org/W1972023576","https://openalex.org/W2350404734","https://openalex.org/W3001418501","https://openalex.org/W2077498359"],"abstract_inverted_index":{"The":[0],"information":[1,39],"on":[2],"the":[3,22,33,45],"spatial":[4],"location":[5,38],"of":[6,24,29],"speakers":[7,30],"can":[8,40],"be":[9,41],"effectively":[10],"used":[11,42],"for":[12],"multi-channel":[13],"speaker":[14,66],"separation.":[15],"For":[16],"example,":[17],"Location-Based":[18],"Training":[19,62],"(LBT)":[20],"uses":[21],"order":[23],"azimuth":[25],"angles":[26],"and":[27,59,68,86],"distances":[28],"to":[31,43],"solve":[32],"permutation":[34],"ambiguity":[35],"problem.":[36],"This":[37,49],"improve":[44],"separation":[46,67],"performance":[47],"further.":[48],"paper":[50],"proposes":[51],"a":[52],"multitask":[53],"learning":[54],"approach,":[55],"Multitask":[56],"Speaker":[57],"Separation":[58],"Direction-of-Arrival":[60,69],"Estimation":[61],"(MSDET),":[63],"jointly":[64],"optimizing":[65],"(DoA)":[70],"estimation.":[71],"In":[72],"our":[73],"evaluation":[74],"using":[75],"SMS-WSJ":[76],"dataset,":[77],"it":[78],"outperforms":[79],"LBT":[80],"by":[81],"0.13":[82],"points":[83,88],"in":[84,89],"SI-SDR":[85],"0.35":[87],"ESTOI.":[90]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}