{"id":"https://openalex.org/W3097819393","doi":"https://doi.org/10.21437/interspeech.2020-1772","title":"Speaker Re-Identification with Speaker Dependent Speech Enhancement","display_name":"Speaker Re-Identification with Speaker Dependent Speech Enhancement","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097819393","doi":"https://doi.org/10.21437/interspeech.2020-1772","mag":"3097819393"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1772","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5088459219","display_name":"Yanpei Shi","orcid":"https://orcid.org/0000-0001-8157-2630"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yanpei Shi","raw_affiliation_strings":["Speech and Hearing Research Group Department of Computer Science, University of Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group Department of Computer Science, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013817745","display_name":"Qiang Huang","orcid":"https://orcid.org/0000-0003-1120-4685"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qiang Huang","raw_affiliation_strings":["Speech and Hearing Research Group Department of Computer Science, University of Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group Department of Computer Science, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030528300","display_name":"Thomas Hain","orcid":"https://orcid.org/0000-0003-0939-3464"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Hain","raw_affiliation_strings":["Speech and Hearing Research Group Department of Computer Science, University of Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group Department of Computer Science, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":0.3286,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.50972411,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1530","last_page":"1534"},"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":0.9997000098228455,"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":0.9979000091552734,"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/speaker-identification","display_name":"Speaker identification","score":0.8587342500686646},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7161356210708618},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7070814371109009},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6833202242851257},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6122643947601318},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6084684133529663}],"concepts":[{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.8587342500686646},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7161356210708618},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7070814371109009},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6833202242851257},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6122643947601318},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6084684133529663},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1772","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.47999998927116394,"display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1481604723","https://openalex.org/W1543643713","https://openalex.org/W1552314771","https://openalex.org/W1982599741","https://openalex.org/W2039240409","https://openalex.org/W2046056978","https://openalex.org/W2064364374","https://openalex.org/W2067295501","https://openalex.org/W2121061347","https://openalex.org/W2165084404","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2521366245","https://openalex.org/W2726515241","https://openalex.org/W2745640009","https://openalex.org/W2760938034","https://openalex.org/W2799674897","https://openalex.org/W2890964092","https://openalex.org/W2911579794","https://openalex.org/W2916104401","https://openalex.org/W2936689732","https://openalex.org/W2943554574","https://openalex.org/W2946508582","https://openalex.org/W2956042401","https://openalex.org/W2962959915","https://openalex.org/W2963341071","https://openalex.org/W2963697785","https://openalex.org/W2972425344","https://openalex.org/W2972481755","https://openalex.org/W2972621414","https://openalex.org/W2973196014","https://openalex.org/W4287869093","https://openalex.org/W4289750118"],"related_works":["https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W36105149","https://openalex.org/W1509309911","https://openalex.org/W2545131480","https://openalex.org/W2249138175","https://openalex.org/W1940231550","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W4401661962"],"abstract_inverted_index":{"While":[0],"the":[1,57,71,76,81,97,127],"use":[2],"of":[3,113],"deep":[4],"neural":[5],"networks":[6],"has":[7],"significantly":[8],"boosted":[9],"speaker":[10,55,61,104,131,138],"recognition":[11,105,139],"performance,":[12],"it":[13],"is":[14,64,68,94],"still":[15],"challenging":[16],"to":[17,42,74,102],"separate":[18],"speakers":[19],"in":[20,70,85,106,147],"poor":[21],"acoustic":[22],"environments.Here":[23],"speech":[24,38,52,77,133,141],"enhancement":[25,39,53,134,142],"methods":[26],"have":[27,34],"traditionally":[28],"allowed":[29],"improved":[30],"performance.The":[31],"recent":[32],"works":[33],"shown":[35],"that":[36,50,126],"adapting":[37],"can":[40,135],"lead":[41],"further":[43],"gains.This":[44],"paper":[45],"introduces":[46],"a":[47,60],"novel":[48],"approach":[49,93,129],"cascades":[51],"and":[54,79,140],"recognition.In":[56],"first":[58],"step,":[59],"embedding":[62],"vector":[63],"generated":[65],",":[66],"which":[67,100],"used":[69],"second":[72],"step":[73],"enhance":[75],"quality":[78],"re-identify":[80],"speakers.Models":[82],"are":[83],"trained":[84],"an":[86],"integrated":[87],"framework":[88],"with":[89],"joint":[90],"optimisation.The":[91],"proposed":[92,128],"evaluated":[95],"using":[96,130],"Voxceleb1":[98],"dataset,":[99],"aims":[101],"assess":[103],"real":[107],"world":[108],"situations.In":[109],"addition":[110],"three":[111],"types":[112],"noise":[114,149],"at":[115],"different":[116],"signal-noise-ratios":[117],"were":[118],"added":[119],"for":[120],"this":[121],"work.The":[122],"obtained":[123],"results":[124],"show":[125],"dependent":[132],"yield":[136],"better":[137],"performances":[143],"than":[144],"two":[145],"baselines":[146],"various":[148],"conditions.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}