{"id":"https://openalex.org/W4224919008","doi":"https://doi.org/10.1109/icassp43922.2022.9747878","title":"Learning Decoupling Features Through Orthogonality Regularization","display_name":"Learning Decoupling Features Through Orthogonality Regularization","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224919008","doi":"https://doi.org/10.1109/icassp43922.2022.9747878"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747878","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5100336156","display_name":"Li Wang","orcid":"https://orcid.org/0000-0003-0357-5056"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Li Wang","raw_affiliation_strings":["Peking University,ADSPLAB, School of ECE,Shenzhen,China","ADSPLAB, School of ECE, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University,ADSPLAB, School of ECE,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"ADSPLAB, School of ECE, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038895203","display_name":"Rongzhi Gu","orcid":"https://orcid.org/0000-0003-1861-9170"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongzhi Gu","raw_affiliation_strings":["Peking University,ADSPLAB, School of ECE,Shenzhen,China","ADSPLAB, School of ECE, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University,ADSPLAB, School of ECE,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"ADSPLAB, School of ECE, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113987256","display_name":"Weiji Zhuang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiji Zhuang","raw_affiliation_strings":["Xiaomi Inc.,Beijing,China","Xiaomi Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Inc.,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Xiaomi Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073011099","display_name":"Peng Gao","orcid":"https://orcid.org/0009-0006-6593-2150"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Gao","raw_affiliation_strings":["Xiaomi Inc.,Beijing,China","Xiaomi Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Inc.,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Xiaomi Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362608","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0003-2335-0946"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiaomi Inc.,Beijing,China","Xiaomi Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Inc.,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Xiaomi Inc., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002795838","display_name":"Yuexian Zou","orcid":"https://orcid.org/0000-0001-9999-6140"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexian Zou","raw_affiliation_strings":["Peking University,ADSPLAB, School of ECE,Shenzhen,China","ADSPLAB, School of ECE, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University,ADSPLAB, School of ECE,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"ADSPLAB, School of ECE, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100336156"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.3118,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.47592114,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7562","last_page":"7566"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9962999820709229,"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":0.9929999709129333,"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/computer-science","display_name":"Computer science","score":0.780608594417572},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.7799344658851624},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6584056615829468},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6023169755935669},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.5960898995399475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5728315114974976},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5578855276107788},{"id":"https://openalex.org/keywords/orthogonality","display_name":"Orthogonality","score":0.5513238906860352},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.49288225173950195},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4520553946495056},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3978020250797272},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38186025619506836},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3204120993614197},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11633941531181335}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.780608594417572},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.7799344658851624},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6584056615829468},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6023169755935669},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.5960898995399475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5728315114974976},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5578855276107788},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.5513238906860352},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.49288225173950195},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4520553946495056},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3978020250797272},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38186025619506836},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3204120993614197},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11633941531181335},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747878","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1553469512","https://openalex.org/W2034940213","https://openalex.org/W2074671152","https://openalex.org/W2121750345","https://openalex.org/W2407023693","https://openalex.org/W2519878990","https://openalex.org/W2566925314","https://openalex.org/W2797583228","https://openalex.org/W2802973008","https://openalex.org/W2889182547","https://openalex.org/W2890964092","https://openalex.org/W2963103976","https://openalex.org/W2963414149","https://openalex.org/W2964187693","https://openalex.org/W2972613398","https://openalex.org/W2972792496","https://openalex.org/W2972909277","https://openalex.org/W2973226577","https://openalex.org/W2987228815","https://openalex.org/W3096976027","https://openalex.org/W3097073596","https://openalex.org/W3148564648","https://openalex.org/W3162342118","https://openalex.org/W6750665317","https://openalex.org/W6754932287","https://openalex.org/W6769728370","https://openalex.org/W6777440055"],"related_works":["https://openalex.org/W4235705411","https://openalex.org/W1521299571","https://openalex.org/W2134501921","https://openalex.org/W204267554","https://openalex.org/W2147062549","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W4317103504","https://openalex.org/W3096066489","https://openalex.org/W3119184205"],"abstract_inverted_index":{"Keyword":[0],"spotting":[1],"(KWS)":[2],"and":[3,20,43,80,90,106,113,145,149],"speaker":[4,45,115],"verification":[5],"(SV)":[6],"are":[7,23,117,121],"two":[8],"important":[9,55],"tasks":[10],"in":[11,72],"speech":[12],"applications.":[13],"Research":[14],"shows":[15],"that":[16,60,132],"the":[17,44,84,102,133,137],"state-of-art":[18],"KWS":[19,105,148],"SV":[21,81,107],"models":[22],"trained":[24],"independently":[25],"using":[26],"different":[27],"datasets":[28],"since":[29],"they":[30],"expect":[31],"to":[32,56,99,139],"learn":[33],"distinctive":[34],"acoustic":[35],"features.":[36,69],"However,":[37],"humans":[38],"can":[39,61],"distinguish":[40],"language":[41],"content":[42],"identity":[46],"simultaneously.":[47],"Motivated":[48],"by":[49],"this,":[50],"we":[51],"believe":[52],"it":[53],"is":[54,88,97],"explore":[57],"a":[58,74,91],"method":[59,96],"effectively":[62],"extract":[63],"common":[64],"features":[65],"while":[66],"decoupling":[67,93],"task-specific":[68],"Bearing":[70],"this":[71],"mind,":[73],"two-branch":[75],"deep":[76],"network":[77,86,138],"(KWS":[78],"branch":[79],"branch)":[82],"with":[83],"same":[85],"structure":[87],"developed":[89],"novel":[92],"feature":[94],"learning":[95],"proposed":[98],"push":[100],"up":[101],"performance":[103],"of":[104,143],"simultaneously":[108],"where":[109],"speaker-invariant":[110],"keyword":[111],"representations":[112,116],"keyword-invariant":[114],"expected":[118],"respectively.":[119,151],"Experiments":[120],"conducted":[122],"on":[123,147],"Google":[124],"Speech":[125],"Commands":[126],"Dataset":[127],"(GSCD).":[128],"The":[129],"results":[130],"demonstrate":[131],"orthogonality":[134],"regularization":[135],"helps":[136],"achieve":[140],"SOTA":[141],"EER":[142],"1.31%":[144],"1.87%":[146],"SV,":[150]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}