{"id":"https://openalex.org/W4372260254","doi":"https://doi.org/10.1109/icassp49357.2023.10096711","title":"Breaking the Trade-Off in Personalized Speech Enhancement With Cross-Task Knowledge Distillation","display_name":"Breaking the Trade-Off in Personalized Speech Enhancement With Cross-Task Knowledge Distillation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260254","doi":"https://doi.org/10.1109/icassp49357.2023.10096711"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096711","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096711","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/A5073861062","display_name":"Hassan Taherian","orcid":"https://orcid.org/0000-0002-7548-3081"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hassan Taherian","raw_affiliation_strings":["Microsoft, Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026088950","display_name":"\u015eefik Emre Eskimez","orcid":"https://orcid.org/0000-0001-6259-5925"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sefik Emre Eskimez","raw_affiliation_strings":["Microsoft, Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft, Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.996999979019165,"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":0.7666288614273071},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6857474446296692},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6829969882965088},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5991031527519226},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5694025754928589},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.439877986907959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3352607488632202},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.09084779024124146},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07059431076049805}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7666288614273071},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6857474446296692},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6829969882965088},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5991031527519226},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5694025754928589},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.439877986907959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3352607488632202},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09084779024124146},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07059431076049805},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096711","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096711","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2141998673","https://openalex.org/W2593116425","https://openalex.org/W2770119437","https://openalex.org/W2936774411","https://openalex.org/W2987307811","https://openalex.org/W3015636705","https://openalex.org/W3094806148","https://openalex.org/W3096090308","https://openalex.org/W3142516134","https://openalex.org/W3193786050","https://openalex.org/W3197042120","https://openalex.org/W3198543387","https://openalex.org/W3198575250","https://openalex.org/W3206706278","https://openalex.org/W3207728800","https://openalex.org/W4224919629","https://openalex.org/W4224925682","https://openalex.org/W4226185896","https://openalex.org/W4296070363","https://openalex.org/W6746278845"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2120771489","https://openalex.org/W2904739811","https://openalex.org/W2275432853","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Personalized":[0],"speech":[1,11,21,29,39,50,72,118,154],"enhancement":[2,12],"(PSE)":[3],"models":[4,13,33,44],"achieve":[5],"promising":[6],"results":[7,167],"compared":[8],"with":[9,129],"unconditional":[10,28],"due":[14],"to":[15,18,24,47,99,114,148,150,159],"their":[16],"ability":[17],"remove":[19,36],"interfering":[20,49,163],"in":[22],"addition":[23],"background":[25],"noise.":[26],"Unlike":[27],"enhancement,":[30],"causal":[31],"PSE":[32,43,65,91,137,172],"may":[34],"occasionally":[35],"the":[37,52,82,85,116,126,136,146,152],"target":[38,53,127],"by":[40,77,162],"mistake.":[41],"The":[42],"also":[45],"tend":[46],"leak":[48],"when":[51,155],"speaker":[54,128],"is":[55,157],"silent":[56],"for":[57],"an":[58],"extended":[59],"period.":[60],"We":[61,87],"show":[62],"that":[63,120],"existing":[64],"methods":[66],"suffer":[67],"from":[68,139],"a":[69,89,106],"trade-off":[70],"between":[71],"over-suppression":[73],"and":[74],"interference":[75],"leakage":[76],"addressing":[78],"one":[79],"problem":[80],"at":[81],"expense":[83],"of":[84],"other.":[86],"propose":[88],"new":[90],"model":[92,138,147],"training":[93,113],"framework":[94],"using":[95],"cross-task":[96],"knowledge":[97],"distillation":[98],"mitigate":[100],"this":[101],"trade-off.":[102],"Specifically,":[103],"we":[104],"utilize":[105],"personalized":[107],"voice":[108],"activity":[109],"detector":[110],"(pVAD)":[111],"during":[112],"exclude":[115],"non-target":[117],"frames":[119],"are":[121,168],"wrongly":[122],"identified":[123],"as":[124],"containing":[125],"hard":[130],"or":[131],"soft":[132],"classification.":[133],"This":[134],"prevents":[135],"being":[140],"too":[141],"aggressive":[142],"while":[143],"still":[144],"allowing":[145],"learn":[149],"suppress":[151],"input":[153],"it":[156],"likely":[158],"be":[160],"spoken":[161],"speakers.":[164],"Comprehensive":[165],"evaluation":[166],"presented,":[169],"covering":[170],"various":[171],"usage":[173],"scenarios.":[174]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
