{"id":"https://openalex.org/W4403126590","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694625","title":"A Unified Approach to Speaker Separation and Target Speaker Extraction Using Encoder-Decoder Based Attractors","display_name":"A Unified Approach to Speaker Separation and Target Speaker Extraction Using Encoder-Decoder Based Attractors","publication_year":2024,"publication_date":"2024-09-09","ids":{"openalex":"https://openalex.org/W4403126590","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694625"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc61483.2024.10694625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","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/A5004929413","display_name":"Srikanth Raj Chetupalli","orcid":"https://orcid.org/0000-0002-2186-5420"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Srikanth Raj Chetupalli","raw_affiliation_strings":["International Audio Laboratories Erlangen,Erlangen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen,Erlangen,Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031626756","display_name":"Emanu\u00ebl A. P. Habets","orcid":"https://orcid.org/0000-0002-2613-8046"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Emanu\u00ebl A. P. Habets","raw_affiliation_strings":["International Audio Laboratories Erlangen,Erlangen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen,Erlangen,Germany","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210123192"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14092986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"190","last_page":"194"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9944999814033508,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9944999814033508,"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/T10860","display_name":"Speech and Audio Processing","score":0.9883000254631042,"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":0.7209805250167847},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6917776465415955},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5124407410621643},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4937842786312103},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.46538132429122925},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4551349878311157},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4335542321205139},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3594750165939331},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.05922222137451172}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7209805250167847},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6917776465415955},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5124407410621643},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4937842786312103},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.46538132429122925},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4551349878311157},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4335542321205139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3594750165939331},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.05922222137451172},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc61483.2024.10694625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2221409856","https://openalex.org/W2734774145","https://openalex.org/W2891833136","https://openalex.org/W2936302822","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W3016361963","https://openalex.org/W3095212884","https://openalex.org/W3099330747","https://openalex.org/W3103434036","https://openalex.org/W3137249133","https://openalex.org/W3163652268","https://openalex.org/W3198575250","https://openalex.org/W4226115251","https://openalex.org/W4297841822","https://openalex.org/W4366503942","https://openalex.org/W4367597591","https://openalex.org/W4391021717","https://openalex.org/W6793651609","https://openalex.org/W6810827206"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W4235705411","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W2407001684","https://openalex.org/W3096066489","https://openalex.org/W3119184205"],"abstract_inverted_index":{"Blind":[0],"speaker":[1,6,14,51,79],"separation":[2,55,59],"(SS)":[3],"and":[4,28,47,53,138],"target":[5,122],"extraction":[7,12],"(TSE)":[8],"deal":[9],"with":[10,74,141],"the":[11,36,67,84,98,105,116,121,126,131,134],"of":[13,120,133],"signals":[15],"from":[16,83],"mixtures":[17,129],"containing":[18],"multiple":[19],"speakers.":[20],"We":[21,65,87],"propose":[22],"a":[23,70],"unified":[24,136],"approach":[25],"to":[26,94,114],"SS":[27,41,137],"TSE":[29,37,99,139],"that":[30,89,110],"requires":[31],"no":[32],"explicit":[33],"training":[34],"for":[35,49,78],"task.":[38],"The":[39],"considered":[40],"system":[42,68,140],"is":[43,91,112],"based":[44,61],"on":[45,62],"SepFormer":[46],"trained":[48],"joint":[50],"counting":[52],"source":[54],"using":[56,81,125],"an":[57,75],"internal":[58],"scheme":[60],"Encoder-Decoder-Attractors":[63],"(EDAs).":[64],"train":[66],"in":[69,97,144],"multi-task":[71],"learning":[72],"setup":[73],"additional":[76],"head":[77],"identification":[80],"attractors":[82],"EDA":[85],"module.":[86],"show":[88,109],"it":[90,111],"then":[92],"possible":[93,113],"perform":[95],"inference":[96],"mode":[100],"without":[101],"explicitly":[102],"extracting":[103],"all":[104],"sources.":[106],"Furthermore,":[107],"we":[108],"detect":[115],"presence":[117],"or":[118],"absence":[119],"speaker.":[123],"Evaluation":[124],"synthetic":[127],"speech":[128],"shows":[130],"feasibility":[132],"proposed":[135],"matching":[142],"performance":[143],"both":[145],"configurations.":[146]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}