{"id":"https://openalex.org/W4372341334","doi":"https://doi.org/10.1109/icassp49357.2023.10094767","title":"Speakeraugment: Data Augmentation for Generalizable Source Separation via Speaker Parameter Manipulation","display_name":"Speakeraugment: Data Augmentation for Generalizable Source Separation via Speaker Parameter Manipulation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372341334","doi":"https://doi.org/10.1109/icassp49357.2023.10094767"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100436995","display_name":"Kai Wang","orcid":"https://orcid.org/0000-0002-1617-5804"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Wang","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,Urumqi,China","School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011571577","display_name":"Yuhang Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Yang","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,Urumqi,China","School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024772368","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6604-0951"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,Urumqi,China","Xinjiang Provincial Key Laboratory of Multi-Lingual Information Technology, Urumqi, China","School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Provincial Key Laboratory of Multi-Lingual Information Technology, Urumqi, China","institution_ids":[]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042363663","display_name":"Ying Hu","orcid":"https://orcid.org/0000-0001-7505-1767"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Hu","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,Urumqi,China","School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["National Institute of Information and Communications Technology (NICT),Kyoto,Japan","National Institute of Information and Communications Technology (NICT), Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT),Kyoto,Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9998999834060669,"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":0.9991000294685364,"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/timit","display_name":"TIMIT","score":0.86113041639328},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7937066555023193},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7884459495544434},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7518314719200134},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.61903977394104},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5706542730331421},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5352848768234253},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5230223536491394},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5156909227371216},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.487280011177063},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.47192835807800293},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4671432673931122},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4295845329761505},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42246344685554504},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.41848987340927124},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3428482413291931},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.28939446806907654},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10399797558784485}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.86113041639328},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7937066555023193},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7884459495544434},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7518314719200134},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.61903977394104},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5706542730331421},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5352848768234253},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5230223536491394},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5156909227371216},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.487280011177063},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.47192835807800293},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4671432673931122},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4295845329761505},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42246344685554504},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.41848987340927124},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3428482413291931},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.28939446806907654},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10399797558784485},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50729863","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100931475","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,"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":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1979651826","https://openalex.org/W2116756305","https://openalex.org/W2127143191","https://openalex.org/W2129142580","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2734774145","https://openalex.org/W2803229097","https://openalex.org/W2936423518","https://openalex.org/W2936774411","https://openalex.org/W2939051810","https://openalex.org/W2952218014","https://openalex.org/W2962780374","https://openalex.org/W2962935966","https://openalex.org/W2972541922","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3015700067","https://openalex.org/W3015794161","https://openalex.org/W3016067707","https://openalex.org/W3027008958","https://openalex.org/W3049430014","https://openalex.org/W3093839391","https://openalex.org/W3096893582","https://openalex.org/W3098557217","https://openalex.org/W3099330747","https://openalex.org/W3161766157","https://openalex.org/W3163652268","https://openalex.org/W3185109982","https://openalex.org/W4224933323","https://openalex.org/W4246307810","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6776317298","https://openalex.org/W6777776875","https://openalex.org/W6784499681"],"related_works":["https://openalex.org/W2046217390","https://openalex.org/W4365503437","https://openalex.org/W2362995206","https://openalex.org/W2004825552","https://openalex.org/W2967718153","https://openalex.org/W2262333520","https://openalex.org/W3188427489","https://openalex.org/W2108636611","https://openalex.org/W2189295099","https://openalex.org/W2914064142"],"abstract_inverted_index":{"Existing":[0],"speech":[1,28,82,146,156],"separation":[2,29],"models":[3],"based":[4,128],"on":[5,77],"deep":[6],"learning":[7],"typically":[8],"generalize":[9],"poorly":[10],"due":[11],"to":[12,32,42,61,141,144],"domain":[13,47],"mismatch.":[14,48],"In":[15],"this":[16,151],"paper,":[17],"we":[18],"propose":[19],"SpeakerAugment":[20],"(SA),":[21],"a":[22,59,133],"data":[23,134],"augmentation":[24,135],"method":[25],"for":[26],"generalizable":[27],"that":[30,93,162],"aims":[31],"increase":[33],"the":[34,78,99,126,163],"diversity":[35],"of":[36,46,52,67,80,102],"speaker":[37,44],"identity":[38],"in":[39,155],"training":[40,108],"data,":[41],"mitigate":[43],"mismatch":[45],"The":[49,84,107,117],"SA":[50,85,95,137,154],"consists":[51],"two":[53],"sub-policies:":[54],"(1)":[55],"SA-Vocoder,":[56],"which":[57,71],"uses":[58],"vocoder":[60],"manipulate":[62],"pitch":[63],"and":[64,75,88,158],"formants":[65],"parameters":[66],"speakers.":[68],"(2)":[69],"SA-Spectrum,":[70],"directly":[72],"performs":[73],"pitch-shift":[74],"time-stretch":[76],"spectrum":[79],"each":[81],"signal.":[83],"is":[86,166],"simple":[87],"effective.":[89],"Experimental":[90],"results":[91,160],"show":[92,161],"using":[94],"can":[96],"significantly":[97],"improve":[98],"generalization":[100,164],"ability":[101,165],"models,":[103],"especially":[104],"for:":[105],"1)":[106],"set":[109,120],"with":[110,121],"fewer":[111],"speakers,":[112],"e.g.,":[113,125],"WSJ0-2mix,":[114],"or":[115],"2)":[116],"target":[118],"test":[119,129],"complex":[122],"linguistic":[123],"conditions,":[124],"TIMIT":[127],"set.":[130],"Moreover,":[131],"as":[132],"method,":[136],"has":[138],"good":[139],"potential":[140],"be":[142],"applicable":[143],"other":[145],"related":[147],"tasks.":[148],"We":[149],"validate":[150],"by":[152],"applying":[153],"recognition,":[157],"experimental":[159],"also":[167],"improved.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}