{"id":"https://openalex.org/W4283074506","doi":"https://doi.org/10.21437/interspeech.2022-10767","title":"Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations","display_name":"Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283074506","doi":"https://doi.org/10.21437/interspeech.2022-10767"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10767","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10767","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/A5059753087","display_name":"Hiroshi Sato","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hiroshi Sato","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070624983","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-2519-2032"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsubasa Ochiai","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082466886","display_name":"Naoki Makishima","orcid":"https://orcid.org/0000-0002-7065-315X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoki Makishima","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027118468","display_name":"Mana Ihori","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mana Ihori","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007415728","display_name":"Tomohiro Tanaka","orcid":"https://orcid.org/0000-0002-8884-9089"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Tanaka","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5059753087"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"996","last_page":"1000"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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/T11309","display_name":"Music and Audio Processing","score":0.9811000227928162,"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/robustness","display_name":"Robustness (evolution)","score":0.8371267318725586},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6493805646896362},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47403597831726074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3375278115272522}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8371267318725586},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6493805646896362},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47403597831726074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3375278115272522},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10767","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10767","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":[{"id":"https://metadata.un.org/sdg/10","score":0.7099999785423279,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1755563775","https://openalex.org/W1992475611","https://openalex.org/W2009086942","https://openalex.org/W2127851351","https://openalex.org/W2150769028","https://openalex.org/W2221409856","https://openalex.org/W2289394825","https://openalex.org/W2460742184","https://openalex.org/W2734774145","https://openalex.org/W2884797218","https://openalex.org/W2891833136","https://openalex.org/W2939771864","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2962780374","https://openalex.org/W2962866211","https://openalex.org/W2962935966","https://openalex.org/W2964171275","https://openalex.org/W2964238697","https://openalex.org/W2972389417","https://openalex.org/W2972802573","https://openalex.org/W3015636705","https://openalex.org/W3015915076","https://openalex.org/W3034729383","https://openalex.org/W3096090308","https://openalex.org/W3105928222","https://openalex.org/W3123318516","https://openalex.org/W3148386121"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Target":[0],"speech":[1,33,47],"extraction":[2,34,125],"is":[3,77],"a":[4,16,61,104],"technique":[5],"to":[6,69,94,144,161],"extract":[7],"the":[8,22,26,71,97,113,133,151],"target":[9,27,32,46,156],"speaker's":[10],"voice":[11,23],"from":[12],"mixture":[13],"signals":[14],"using":[15],"pre-recorded":[17],"enrollment":[18,50,64,100,122,165],"utterance":[19],"that":[20,108],"characterize":[21],"characteristics":[24,43],"of":[25,31,63,78,135,153],"speaker.One":[28],"major":[29],"difficulty":[30],"lies":[35],"in":[36,39],"handling":[37],"variability":[38],"\"intra-speaker\"":[40],"characteristics,":[41],"i.e.,":[42],"mismatch":[44],"between":[45],"and":[48,158],"an":[49,86],"utterance.While":[51],"most":[52],"conventional":[53],"approaches":[54],"focus":[55],"on":[56,118],"improving":[57],"average":[58],"performance":[59,115],"given":[60],"set":[62],"utterances,":[65],"here":[66],"we":[67,75,84,131],"propose":[68,85],"guarantee":[70],"worst":[72],"performance,":[73],"which":[74],"believe":[76],"great":[79],"practical":[80],"importance.In":[81],"this":[82],"work,":[83],"evaluation":[87],"metric":[88],"called":[89],"worstenrollment":[90],"source-to-distortion":[91],"ratio":[92],"(SDR)":[93],"quantitatively":[95],"measure":[96],"robustness":[98,146,163],"towards":[99],"variations.We":[101],"also":[102],"introduce":[103],"novel":[105],"training":[106,119,157,160],"scheme":[107],"aims":[109],"at":[110],"directly":[111],"optimizing":[112],"worst-case":[114],"by":[116,167],"focusing":[117],"with":[120],"difficult":[121],"cases":[123],"where":[124],"does":[126],"not":[127],"perform":[128],"well.In":[129],"addition,":[130],"investigate":[132],"effectiveness":[134,152],"auxiliary":[136],"speaker":[137,169],"identification":[138],"loss":[139],"(SI-loss)":[140],"as":[141],"another":[142],"way":[143],"improve":[145,162],"over":[147],"enrollments.Experimental":[148],"validation":[149],"reveals":[150],"both":[154],"worst-enrollment":[155],"SI-loss":[159],"against":[164],"variations,":[166],"increasing":[168],"discriminability.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}