{"id":"https://openalex.org/W4408354828","doi":"https://doi.org/10.1109/icassp49660.2025.10887680","title":"Distance Based Single-Channel Target Speech Extraction","display_name":"Distance Based Single-Channel Target Speech Extraction","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354828","doi":"https://doi.org/10.1109/icassp49660.2025.10887680"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5080269657","display_name":"Runwu Shi","orcid":"https://orcid.org/0000-0001-9097-9619"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Runwu Shi","raw_affiliation_strings":["Tokyo Institute of Technology,Dept. of Systems & Control Engineering,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology,Dept. of Systems & Control Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042063575","display_name":"Benjamin Yen","orcid":"https://orcid.org/0000-0002-6958-7319"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Benjamin Yen","raw_affiliation_strings":["Tokyo Institute of Technology,Dept. of Systems & Control Engineering,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology,Dept. of Systems & Control Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041970584","display_name":"Kazuhiro Nakadai","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Nakadai","raw_affiliation_strings":["Tokyo Institute of Technology,Dept. of Systems & Control Engineering,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology,Dept. of Systems & Control Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":3.0416,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.9016956,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":97},"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":0.9873999953269958,"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":0.9873999953269958,"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":0.9799000024795532,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6693089008331299},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5763726830482483},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.47574564814567566},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.42556607723236084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32535243034362793},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1924748718738556}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6693089008331299},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5763726830482483},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.47574564814567566},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.42556607723236084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32535243034362793},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1924748718738556},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2763188033","https://openalex.org/W2901243971","https://openalex.org/W2964058413","https://openalex.org/W2995181338","https://openalex.org/W3015199127","https://openalex.org/W3161934504","https://openalex.org/W3184252821","https://openalex.org/W4294891356","https://openalex.org/W4296070366","https://openalex.org/W4310873168","https://openalex.org/W4367597591","https://openalex.org/W4372259962","https://openalex.org/W4385756463","https://openalex.org/W4385823352","https://openalex.org/W4386764032","https://openalex.org/W4392931251","https://openalex.org/W4395471087","https://openalex.org/W4401023616","https://openalex.org/W6631190155"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"This":[0,17,76],"paper":[1],"aims":[2],"to":[3,82],"achieve":[4],"single-channel":[5,33,38],"target":[6],"speech":[7],"extraction":[8,42],"(TSE)":[9],"in":[10,62,89],"enclosures":[11],"by":[12,36],"solely":[13],"utilizing":[14],"distance":[15,25,52],"information.":[16],"is":[18],"the":[19,69,84],"first":[20],"work":[21],"that":[22,49],"utilizes":[23],"only":[24],"cues":[26],"without":[27],"using":[28],"speaker":[29],"physiological":[30],"information":[31,53],"for":[32,58],"TSE.":[34,59],"Inspired":[35],"recent":[37],"Distance-based":[39],"separation":[40],"and":[41,65,71],"methods,":[43],"we":[44],"introduce":[45],"a":[46],"novel":[47],"model":[48],"efficiently":[50],"fuses":[51],"with":[54],"time-frequency":[55],"(TF)":[56],"bins":[57],"Experimental":[60],"results":[61],"both":[63],"single-room":[64],"multi-room":[66],"scenarios":[67],"demonstrate":[68],"feasibility":[70],"effectiveness":[72],"of":[73,86],"our":[74],"approach.":[75],"method":[77],"can":[78],"also":[79],"be":[80],"employed":[81],"estimate":[83],"distances":[85],"different":[87],"speakers":[88],"mixed":[90],"speech.":[91],"Online":[92],"demos":[93],"are":[94],"available":[95],"at":[96],"https://runwushi.github.io/distance-demo-page/.":[97]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}