{"id":"https://openalex.org/W2931266113","doi":"https://doi.org/10.21437/interspeech.2019-1496","title":"VoiceID Loss: Speech Enhancement for Speaker Verification","display_name":"VoiceID Loss: Speech Enhancement for Speaker Verification","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2931266113","doi":"https://doi.org/10.21437/interspeech.2019-1496","mag":"2931266113"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1496","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.03601","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020263683","display_name":"Suwon Shon","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suwon Shon","raw_affiliation_strings":["Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100662192","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-6877-0226"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Tang","raw_affiliation_strings":["Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2888","last_page":"2892"},"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":0.9983000159263611,"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/robustness","display_name":"Robustness (evolution)","score":0.7702716588973999},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.7269659638404846},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7091955542564392},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.695170521736145},{"id":"https://openalex.org/keywords/pointwise","display_name":"Pointwise","score":0.6825113296508789},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6504639983177185},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.642326831817627},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.44622111320495605},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43517354130744934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27518507838249207},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2197825014591217},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10034659504890442}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7702716588973999},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7269659638404846},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7091955542564392},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.695170521736145},{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.6825113296508789},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6504639983177185},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.642326831817627},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.44622111320495605},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43517354130744934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27518507838249207},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2197825014591217},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10034659504890442},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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":4,"locations":[{"id":"doi:10.21437/interspeech.2019-1496","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.03601","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03601","pdf_url":"https://arxiv.org/pdf/1904.03601","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":"","raw_type":"text"},{"id":"mag:2931266113","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1904.03601.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.1904.03601","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.03601","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.03601","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03601","pdf_url":"https://arxiv.org/pdf/1904.03601","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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2931266113.pdf","grobid_xml":"https://content.openalex.org/works/W2931266113.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W46095808","https://openalex.org/W1956021273","https://openalex.org/W2114925438","https://openalex.org/W2117671523","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2407127962","https://openalex.org/W2746457594","https://openalex.org/W2748488820","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2884412522","https://openalex.org/W2890704021","https://openalex.org/W2897924318","https://openalex.org/W2899754108","https://openalex.org/W2900575527","https://openalex.org/W2962946733","https://openalex.org/W2963371159","https://openalex.org/W2972961496"],"related_works":["https://openalex.org/W2972425344","https://openalex.org/W2747366803","https://openalex.org/W1482185106","https://openalex.org/W3031039208","https://openalex.org/W2772868316","https://openalex.org/W264546557","https://openalex.org/W3016109656","https://openalex.org/W2890964092","https://openalex.org/W3177048943","https://openalex.org/W2823516554","https://openalex.org/W2399672261","https://openalex.org/W3201698955","https://openalex.org/W2921661700","https://openalex.org/W2937932858","https://openalex.org/W3182803800","https://openalex.org/W3082512732","https://openalex.org/W2373027720","https://openalex.org/W2370100170","https://openalex.org/W2783185598","https://openalex.org/W2023936961"],"abstract_inverted_index":{"In":[0,24,77],"this":[1],"paper,":[2],"we":[3,80],"propose":[4],"VoiceID":[5,41,90],"loss,":[6,39,91],"a":[7,13,49,55,96],"novel":[8],"loss":[9,30,42],"function":[10],"for":[11,32,74,108],"training":[12,87],"speech":[14,33],"enhancement":[15,34,84],"model":[16,52,112],"to":[17,26,53,69,94],"improve":[18],"the":[19,27,37,40,46,66,78,83,89,115],"robustness":[20],"of":[21,99],"speaker":[22,50,75,116],"verification.":[23,76,109],"contrast":[25],"commonly":[28],"used":[29],"functions":[31],"such":[35,102],"as":[36,103],"L2":[38],"is":[43,62,92],"based":[44],"on":[45,119],"feedback":[47],"from":[48],"verification":[51,117],"generate":[54],"ratio":[56,60],"mask.":[57],"The":[58,110],"generated":[59],"mask":[61],"multiplied":[63],"pointwise":[64],"with":[65,88],"original":[67],"spectrogram":[68],"filter":[70],"out":[71],"unnecessary":[72],"components":[73],"experiments,":[79],"observed":[81],"that":[82],"network,":[85],"after":[86],"able":[93],"ignore":[95],"substantial":[97],"amount":[98],"time-frequency":[100],"bins,":[101],"those":[104],"dominated":[105],"by":[106],"noise,":[107],"resulting":[111],"consistently":[113],"improves":[114],"system":[118],"both":[120],"clean":[121],"and":[122],"noisy":[123],"conditions.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}