{"id":"https://openalex.org/W4372348071","doi":"https://doi.org/10.1109/icassp49357.2023.10096648","title":"Beamformer-Guided Target Speaker Extraction","display_name":"Beamformer-Guided Target Speaker Extraction","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372348071","doi":"https://doi.org/10.1109/icassp49357.2023.10096648"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096648","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/A5080306514","display_name":"Mohamed Elminshawi","orcid":"https://orcid.org/0000-0003-2737-0602"},"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":true,"raw_author_name":"Mohamed Elminshawi","raw_affiliation_strings":["International Audio Laboratories Erlangen,Erlangen,Germany,91058"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","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,91058"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen,Erlangen,Germany,91058","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,91058"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5080306514"],"corresponding_institution_ids":["https://openalex.org/I4210123192"],"apc_list":null,"apc_paid":null,"fwci":1.4264,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81740219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"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":0.9995999932289124,"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":0.9994000196456909,"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":0.6968318223953247},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5347050428390503},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46029767394065857},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4301331043243408},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4285638630390167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3273070454597473}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6968318223953247},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5347050428390503},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46029767394065857},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4301331043243408},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4285638630390167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3273070454597473},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096648","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2168729028","https://openalex.org/W2398042854","https://openalex.org/W2517616541","https://openalex.org/W2734774145","https://openalex.org/W2944972166","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2963301902","https://openalex.org/W2964058413","https://openalex.org/W2972802573","https://openalex.org/W2973179291","https://openalex.org/W2996820600","https://openalex.org/W3015191643","https://openalex.org/W3015636705","https://openalex.org/W3015788098","https://openalex.org/W3099330747","https://openalex.org/W3116025434","https://openalex.org/W4297841846","https://openalex.org/W6631190155","https://openalex.org/W6762182681","https://openalex.org/W6772027853","https://openalex.org/W6803183793"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W66821593","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W1521299571","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W1516392727","https://openalex.org/W2140022733"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,11,16,32,46],"Beamformer-guided":[3],"Target":[4],"Speaker":[5],"Extraction":[6],"(BG-TSE)":[7],"method":[8,30,62,99],"to":[9,40,45,101],"extract":[10],"target":[12,38],"speaker\u2019s":[13],"voice":[14],"from":[15],"multi-channel":[17,84,105],"recording":[18],"informed":[19],"by":[20],"the":[21,26,37,56,60,65,68,73,77,94,97],"direction":[22],"of":[23,25,96],"arrival":[24],"target.":[27],"The":[28],"proposed":[29,61,98],"employs":[31],"front-end":[33,69],"beamformer":[34,70],"steered":[35],"towards":[36],"speaker":[39],"pro-vide":[41],"an":[42],"auxiliary":[43],"signal":[44],"single-channel":[47,57,103],"TSE":[48,58],"system.":[49],"By":[50],"allowing":[51],"for":[52],"time-varying":[53],"embeddings":[54],"in":[55,76,87],"block,":[59],"fully":[63],"exploits":[64],"correspondence":[66],"between":[67],"output":[71],"and":[72,90,104],"tar-get":[74],"speech":[75],"microphone":[78],"signal.":[79],"Experimental":[80],"evaluation":[81],"on":[82],"simulated":[83],"2-speaker":[85],"mixtures,":[86],"both":[88],"anechoic":[89],"reverberant":[91],"conditions,":[92],"demonstrates":[93],"advantage":[95],"compared":[100],"recent":[102],"baselines.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}