{"id":"https://openalex.org/W4226185896","doi":"https://doi.org/10.21437/interspeech.2022-10962","title":"Fast Real-time Personalized Speech Enhancement: End-to-End Enhancement Network (E3Net) and Knowledge Distillation","display_name":"Fast Real-time Personalized Speech Enhancement: End-to-End Enhancement Network (E3Net) and Knowledge Distillation","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4226185896","doi":"https://doi.org/10.21437/interspeech.2022-10962"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10962","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10962","pdf_url":"https://www.isca-archive.org/interspeech_2022/thakker22_interspeech.pdf","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":true,"oa_status":"bronze","oa_url":"https://www.isca-archive.org/interspeech_2022/thakker22_interspeech.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028363114","display_name":"Manthan Thakker","orcid":null},"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":"Manthan Thakker","raw_affiliation_strings":["Microsoft Corporation , One Microsoft Way , WA , USA","Microsoft Corporation, One Microsoft Way, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation , One Microsoft Way , WA , USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, One Microsoft Way, 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 Corporation , One Microsoft Way , WA , USA","Microsoft Corporation, One Microsoft Way, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation , One Microsoft Way , WA , USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, One Microsoft Way, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","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 Corporation , One Microsoft Way , WA , USA","Microsoft Corporation, One Microsoft Way, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation , One Microsoft Way , WA , USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, One Microsoft Way, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101528071","display_name":"Huaming Wang","orcid":"https://orcid.org/0000-0003-1490-2673"},"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":"Huaming Wang","raw_affiliation_strings":["Microsoft Corporation , One Microsoft Way , WA , USA","Microsoft Corporation, One Microsoft Way, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation , One Microsoft Way , WA , USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, One Microsoft Way, 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":true,"cited_by_count":32,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"991","last_page":"995"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9969000220298767,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9793999791145325,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7958699464797974},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7671757936477661},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5802035927772522},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17699381709098816}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7958699464797974},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7671757936477661},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5802035927772522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17699381709098816},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10962","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10962","pdf_url":"https://www.isca-archive.org/interspeech_2022/thakker22_interspeech.pdf","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":{"id":"doi:10.21437/interspeech.2022-10962","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10962","pdf_url":"https://www.isca-archive.org/interspeech_2022/thakker22_interspeech.pdf","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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4226185896.pdf","grobid_xml":"https://content.openalex.org/works/W4226185896.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2593116425","https://openalex.org/W2770119437","https://openalex.org/W2803023299","https://openalex.org/W2952218014","https://openalex.org/W2975429091","https://openalex.org/W2978017171","https://openalex.org/W2987861506","https://openalex.org/W3096090308","https://openalex.org/W3101327063","https://openalex.org/W3114898335","https://openalex.org/W3193846000","https://openalex.org/W3194338569","https://openalex.org/W3197042120","https://openalex.org/W3198543387","https://openalex.org/W3204510963","https://openalex.org/W3206706278","https://openalex.org/W3207728800","https://openalex.org/W4206375145","https://openalex.org/W4225302959","https://openalex.org/W4226128078","https://openalex.org/W4304206546","https://openalex.org/W4324109905"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W3196421258","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2151749779","https://openalex.org/W2382290278","https://openalex.org/W2938107654"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"how":[3],"to":[4,49],"improve":[5],"the":[6,17,70,107,113,126,136,143],"runtime":[7],"speed":[8],"of":[9],"personalized":[10],"speech":[11,84,94,144],"enhancement":[12,32],"(PSE)":[13],"networks":[14],"while":[15],"maintaining":[16],"model":[18,34],"quality.Our":[19],"approach":[20],"includes":[21],"two":[22],"aspects:":[23],"architecture":[24],"and":[25,95,128,133,138],"knowledge":[26],"distillation":[27],"(KD).We":[28],"propose":[29],"an":[30,82],"end-to-end":[31],"(E3Net)":[33],"architecture,":[35],"which":[36],"is":[37],"3\u00d7":[38],"faster":[39,124],"than":[40,106,125],"a":[41,99],"baseline":[42,108],"STFT-based":[43],"model.Besides,":[44],"we":[45,59,74,110],"use":[46],"KD":[47,76,114,132],"techniques":[48],"develop":[50],"compressed":[51],"student":[52,71,118],"models":[53,119],"without":[54,64,141],"significantly":[55],"degrading":[56,142],"quality.In":[57],"addition,":[58],"investigate":[60],"using":[61,81],"noisy":[62],"data":[63],"reference":[65],"clean":[66],"signals":[67],"for":[68],"training":[69],"models,":[72],"where":[73],"combine":[75],"with":[77,98],"multi-task":[78],"learning":[79],"(MTL)":[80],"automatic":[83],"recognition":[85],"(ASR)":[86],"loss.Our":[87],"results":[88],"show":[89,111],"that":[90,112,120],"E3Net":[91],"provides":[92,129],"better":[93],"transcription":[96],"quality":[97],"lower":[100],"target":[101],"speaker":[102],"over-suppression":[103],"(TSOS)":[104],"rate":[105],"model.Furthermore,":[109],"methods":[115],"can":[116],"yield":[117],"are":[121],"2":[122],"-4\u00d7":[123],"teacher":[127],"reasonable":[130],"quality.Combining":[131],"MTL":[134],"improves":[135],"ASR":[137],"TSOS":[139],"metrics":[140],"quality.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":13}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}