{"id":"https://openalex.org/W3167217740","doi":"https://doi.org/10.21437/interspeech.2021-694","title":"Personalized PercepNet: Real-Time, Low-Complexity Target Voice Separation and Enhancement","display_name":"Personalized PercepNet: Real-Time, Low-Complexity Target Voice Separation and Enhancement","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3167217740","doi":"https://doi.org/10.21437/interspeech.2021-694","mag":"3167217740"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-694","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.04129","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091775011","display_name":"Ritwik Giri","orcid":"https://orcid.org/0000-0002-8599-3229"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ritwik Giri","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001842601","display_name":"Shrikant Venkataramani","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikant Venkataramani","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, United States","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021269794","display_name":"Jean-Marc Valin","orcid":"https://orcid.org/0000-0002-9883-6927"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jean-Marc Valin","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036092393","display_name":"Umut Isik","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Umut Isik","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112751528","display_name":"Arvindh Krishnaswamy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Arvindh Krishnaswamy","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4633,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.60494075,"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":"1124","last_page":"1128"},"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":0.9998000264167786,"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":0.9983999729156494,"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":0.7505845427513123},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6919569373130798},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6909870505332947},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6396887898445129},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4921976625919342},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4668142795562744},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4199325144290924},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41987094283103943},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4108901619911194},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.383181631565094},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20891809463500977},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07893764972686768}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7505845427513123},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6919569373130798},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6909870505332947},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6396887898445129},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4921976625919342},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4668142795562744},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4199325144290924},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41987094283103943},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4108901619911194},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.383181631565094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20891809463500977},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07893764972686768}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-694","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.04129","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.04129","pdf_url":"https://arxiv.org/pdf/2106.04129","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3167217740","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.04129.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2106.04129","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.04129","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.04129","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.04129","pdf_url":"https://arxiv.org/pdf/2106.04129","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3167217740.pdf","grobid_xml":"https://content.openalex.org/works/W3167217740.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1495679096","https://openalex.org/W2221409856","https://openalex.org/W2726515241","https://openalex.org/W2734774145","https://openalex.org/W2749510669","https://openalex.org/W2808631503","https://openalex.org/W2896538040","https://openalex.org/W2899515918","https://openalex.org/W2949281321","https://openalex.org/W2952218014","https://openalex.org/W2952752702","https://openalex.org/W2962788625","https://openalex.org/W2962935966","https://openalex.org/W2963091184","https://openalex.org/W2963432880","https://openalex.org/W2972802573","https://openalex.org/W2973062255","https://openalex.org/W3000358149","https://openalex.org/W3002439978","https://openalex.org/W3015915076","https://openalex.org/W3024085360","https://openalex.org/W3092864146","https://openalex.org/W3094831814","https://openalex.org/W3096090308","https://openalex.org/W3097034112","https://openalex.org/W3097353642","https://openalex.org/W3163464523","https://openalex.org/W3209141406"],"related_works":["https://openalex.org/W3198543387","https://openalex.org/W3211614993","https://openalex.org/W3005914302","https://openalex.org/W2976460547","https://openalex.org/W3016048045","https://openalex.org/W2055575468","https://openalex.org/W3029282897","https://openalex.org/W3162424266","https://openalex.org/W2339276216","https://openalex.org/W3163929126","https://openalex.org/W2407564530","https://openalex.org/W3203327585","https://openalex.org/W3175000095","https://openalex.org/W3197227964","https://openalex.org/W3206706278","https://openalex.org/W3133801870","https://openalex.org/W3094460521","https://openalex.org/W2765233562","https://openalex.org/W3015810999","https://openalex.org/W3087422378"],"abstract_inverted_index":{"The":[0],"presence":[1],"of":[2,52,126],"multiple":[3],"talkers":[4],"in":[5,124],"the":[6,19,53,82,88,101,114],"surrounding":[7],"environment":[8],"poses":[9],"a":[10,33,40,44,69,77],"difficult":[11],"challenge":[12],"for":[13,81],"real-time":[14,34],"speech":[15,35,60,128],"communication":[16],"systems":[17],"considering":[18],"constraints":[20],"on":[21,50],"network":[22,74],"size":[23],"and":[24,98,120,131],"complexity.":[25],"In":[26],"this":[27],"paper,":[28],"we":[29,62,66],"present":[30],"Personalized":[31,85],"PercepNet,":[32],"enhancement":[36,129],"model":[37,116],"that":[38,113],"separates":[39],"target":[41,89,102],"speaker":[42,72,90,103],"from":[43],"noisy":[45],"multi-talker":[46],"mixture":[47],"without":[48],"compromising":[49],"complexity":[51],"recently":[54],"proposed":[55,115],"PercepNet.":[56],"To":[57],"enable":[58],"speaker-dependent":[59],"enhancement,":[61],"first":[63],"show":[64,112],"how":[65],"can":[67],"train":[68],"perceptually":[70],"motivated":[71],"embedder":[73],"to":[75,95],"produce":[76],"representative":[78],"embedding":[79,91],"vector":[80],"given":[83],"speaker.":[84],"PercepNet":[86,119],"uses":[87],"as":[92],"additional":[93],"information":[94],"pick":[96],"out":[97],"enhance":[99],"only":[100],"while":[104],"suppressing":[105],"all":[106],"other":[107,121],"competing":[108],"sounds.":[109],"Our":[110],"experiments":[111],"significantly":[117],"outperforms":[118],"baselines,":[122],"both":[123],"terms":[125],"objective":[127],"metrics":[130],"human":[132],"opinion":[133],"scores.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}