{"id":"https://openalex.org/W4372265824","doi":"https://doi.org/10.1109/icassp49357.2023.10096478","title":"Quantitative Evidence on Overlooked Aspects of Enrollment Speaker Embeddings for Target Speaker Separation","display_name":"Quantitative Evidence on Overlooked Aspects of Enrollment Speaker Embeddings for Target Speaker Separation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372265824","doi":"https://doi.org/10.1109/icassp49357.2023.10096478"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096478","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":"article","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/A5100455531","display_name":"Xiaoyu Liu","orcid":"https://orcid.org/0009-0005-6402-3855"},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Xiaoyu Liu","raw_affiliation_strings":["Dolby Laboratories"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342504","display_name":"Xu Li","orcid":"https://orcid.org/0009-0004-7507-4669"},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Xu Li","raw_affiliation_strings":["Dolby Laboratories"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044197796","display_name":"Joan Serr\u00e0","orcid":null},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Joan Serr\u00e0","raw_affiliation_strings":["Dolby Laboratories"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100455531"],"corresponding_institution_ids":["https://openalex.org/I116121188"],"apc_list":null,"apc_paid":null,"fwci":2.0144,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87097374,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"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":0.9998000264167786,"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":0.9991999864578247,"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/generalization","display_name":"Generalization","score":0.7723370790481567},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7094934582710266},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6244722008705139},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5902886986732483},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.572313129901886},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5634171366691589},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5517374277114868},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.5337121486663818},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5288283228874207},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5266494750976562},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4768701195716858},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.466288298368454},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41170045733451843},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4101484417915344},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23781561851501465},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1536741554737091},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08909907937049866}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7723370790481567},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7094934582710266},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6244722008705139},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5902886986732483},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.572313129901886},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5634171366691589},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5517374277114868},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.5337121486663818},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5288283228874207},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5266494750976562},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4768701195716858},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.466288298368454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41170045733451843},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4101484417915344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23781561851501465},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1536741554737091},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08909907937049866},{"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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096478","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":0.8700000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1547166023","https://openalex.org/W2726515241","https://openalex.org/W2760103357","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W2938646939","https://openalex.org/W2952218014","https://openalex.org/W2962788625","https://openalex.org/W2969985801","https://openalex.org/W2973062255","https://openalex.org/W2995181338","https://openalex.org/W2998572311","https://openalex.org/W3015213852","https://openalex.org/W3015302980","https://openalex.org/W3015306128","https://openalex.org/W3015636705","https://openalex.org/W3015700067","https://openalex.org/W3024869864","https://openalex.org/W3036601975","https://openalex.org/W3096408984","https://openalex.org/W3097353642","https://openalex.org/W3099330747","https://openalex.org/W3197580070","https://openalex.org/W3198543387","https://openalex.org/W3206706278","https://openalex.org/W3207728800","https://openalex.org/W3209059054","https://openalex.org/W3209185908","https://openalex.org/W4224919629","https://openalex.org/W4224933800","https://openalex.org/W4225592424","https://openalex.org/W4225905067","https://openalex.org/W4226185896","https://openalex.org/W4226296260","https://openalex.org/W4288091954","https://openalex.org/W4385245566","https://openalex.org/W6632679785","https://openalex.org/W6739901393","https://openalex.org/W6769178842","https://openalex.org/W6772349387","https://openalex.org/W6777437564","https://openalex.org/W6780218876","https://openalex.org/W6803308325","https://openalex.org/W6811237677"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Single":[0],"channel":[1],"target":[2],"speaker":[3,39,75,98,129],"separation":[4,48,144],"(TSS)":[5],"aims":[6],"at":[7],"extracting":[8],"a":[9,13,42,107,139],"speaker\u2019s":[10],"voice":[11],"from":[12],"mixture":[14],"of":[15,22,32,64,71,80,127,148],"multiple":[16],"talkers":[17],"given":[18],"an":[19,33],"enrollment":[20,38,66],"utterance":[21],"that":[23,36,45,96],"speaker.":[24],"A":[25],"typical":[26],"deep":[27],"learning":[28],"TSS":[29],"framework":[30],"consists":[31],"upstream":[34,166],"model":[35,44],"obtains":[37],"embeddings":[40,100,123],"and":[41,84,87,120,145],"downstream":[43],"performs":[46],"the":[47,51,65,69,72,78,81,88,97,118,121,125,128,132,136,149],"conditioned":[49],"on":[50,164],"embeddings.":[52],"In":[53,115],"this":[54],"paper,":[55],"we":[56],"look":[57],"into":[58],"several":[59],"important":[60],"but":[61,131],"overlooked":[62],"aspects":[63],"embeddings,":[67,77,86],"including":[68],"suitability":[70],"widely":[73],"used":[74],"identification":[76,99],"introduction":[79],"log-mel":[82],"filterbank":[83,119,152],"self-supervised":[85,122],"embeddings\u2019":[89],"cross-dataset":[90,140],"generalization":[91,146],"capability.":[92],"Our":[93],"results":[94],"show":[95],"could":[101],"lose":[102],"relevant":[103],"information":[104],"due":[105],"to":[106],"sub-optimal":[108],"metric,":[109],"training":[110],"objective,":[111],"or":[112],"common":[113],"pre-processing.":[114],"contrast,":[116],"both":[117],"preserve":[124],"integrity":[126],"information,":[130],"former":[133],"consistently":[134],"out-performs":[135],"latter":[137],"in":[138],"evaluation.":[141],"The":[142],"competitive":[143],"performance":[147],"previously":[150],"over-looked":[151],"embedding":[153],"is":[154],"consistent":[155],"across":[156],"our":[157],"study,":[158],"which":[159],"calls":[160],"for":[161],"future":[162],"research":[163],"better":[165],"features.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}