{"id":"https://openalex.org/W3197629192","doi":"https://doi.org/10.21437/interspeech.2021-298","title":"Improving Channel Decorrelation for Multi-Channel Target Speech Extraction","display_name":"Improving Channel Decorrelation for Multi-Channel Target Speech Extraction","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197629192","doi":"https://doi.org/10.21437/interspeech.2021-298","mag":"3197629192"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-298","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5090367911","display_name":"Jiangyu Han","orcid":"https://orcid.org/0000-0001-5390-8520"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiangyu Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035226758","display_name":"Wei Rao","orcid":"https://orcid.org/0000-0002-7237-0874"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Rao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084128157","display_name":"Yannan Wang","orcid":"https://orcid.org/0000-0001-7248-4954"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yannan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056415893","display_name":"Yanhua Long","orcid":"https://orcid.org/0000-0003-0924-408X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanhua Long","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9265,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.7464685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1847","last_page":"1851"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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":0.9962000250816345,"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/decorrelation","display_name":"Decorrelation","score":0.9246789216995239},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7499054670333862},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6153041124343872},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6118343472480774},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5795331001281738},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5143207311630249},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46742743253707886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44737374782562256},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23670417070388794},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13984808325767517}],"concepts":[{"id":"https://openalex.org/C177860922","wikidata":"https://www.wikidata.org/wiki/Q788608","display_name":"Decorrelation","level":2,"score":0.9246789216995239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7499054670333862},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6153041124343872},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6118343472480774},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5795331001281738},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5143207311630249},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46742743253707886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44737374782562256},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23670417070388794},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13984808325767517},{"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:10.21437/interspeech.2021-298","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1604939135","https://openalex.org/W2127058578","https://openalex.org/W2735368845","https://openalex.org/W2089764958","https://openalex.org/W2073586885","https://openalex.org/W2546477360","https://openalex.org/W2359691516","https://openalex.org/W2098040275","https://openalex.org/W2261979314","https://openalex.org/W3109905219"],"abstract_inverted_index":{"Target":[0],"speech":[1,58,164],"extraction":[2,62],"has":[3,50],"attracted":[4],"widespread":[5],"attention.":[6],"When":[7],"microphone":[8],"arrays":[9],"are":[10,130],"available,":[11],"the":[12,21,35,41,47,56,61,68,71,84,87,93,111,118,135,141,152,162],"additional":[13],"spatial":[14,120],"information":[15,38,121,150],"can":[16,144],"be":[17],"helpful":[18],"in":[19,146],"extracting":[20,55],"target":[22,57,123,163],"speech.":[23],"We":[24],"have":[25],"recently":[26],"proposed":[27,48],"a":[28,106],"channel":[29,43,89],"decorrelation":[30,73],"(CD)":[31],"mechanism":[32,49],"to":[33,39,82,160],"extract":[34],"inter-channel":[36,96],"differential":[37,149],"enhance":[40],"reference":[42],"encoder":[44,99,128],"representation.":[45],"Although":[46],"shown":[51],"promising":[52],"results":[53],"for":[54],"from":[59],"mixtures,":[60],"performance":[63],"is":[64,156],"still":[65],"limited":[66],"by":[67,91],"nature":[69],"of":[70,86,117,126],"original":[72,88,94],"theory.":[74],"In":[75],"this":[76],"paper,":[77],"we":[78],"propose":[79],"two":[80],"methods":[81],"broaden":[83],"horizon":[85],"decorrelation,":[90],"replacing":[92],"softmax-based":[95],"similarity":[97,109],"between":[98],"representations,":[100],"using":[101],"an":[102],"unrolled":[103],"probability":[104],"and":[105,122,151],"normalized":[107],"cosine-based":[108],"at":[110],"dimensional-level.":[112],"Moreover,":[113],"new":[114,153],"combination":[115],"strategies":[116],"CD-based":[119],"speaker":[124],"adaptation":[125,154],"parallel":[127],"outputs":[129],"also":[131,157],"investigated.":[132],"Experiments":[133],"on":[134],"reverberant":[136],"WSJ0":[137],"2-mix":[138],"show":[139],"that":[140],"improved":[142],"CD":[143],"result":[145],"more":[147],"discriminative":[148],"strategy":[155],"very":[158],"effective":[159],"improve":[161],"extraction.":[165]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}