{"id":"https://openalex.org/W18454654","doi":"https://doi.org/10.21437/interspeech.2006-20","title":"CASA based speech separation for robust speech recognition","display_name":"CASA based speech separation for robust speech recognition","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W18454654","doi":"https://doi.org/10.21437/interspeech.2006-20","mag":"18454654"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-20","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-20","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","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/A5040610690","display_name":"Runqiang Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Runqiang Han","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103037356","display_name":"Pei Zhao","orcid":"https://orcid.org/0000-0003-2350-3025"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pei Zhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079489298","display_name":"Qin Gao","orcid":"https://orcid.org/0000-0002-0573-9774"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin Gao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389496","display_name":"Zhiping Zhang","orcid":"https://orcid.org/0009-0008-0452-3147"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiping Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022976382","display_name":"Hao Wu","orcid":"https://orcid.org/0000-0001-8052-7707"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084685506","display_name":"Xihong Wu","orcid":"https://orcid.org/0009-0004-5236-7469"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xihong Wu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5040610690"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2721,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.77248282,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"paper 2068","last_page":"Mon1WeS.2"},"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/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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8195387721061707},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7672969102859497},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.547797441482544},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5406318306922913},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4953421652317047},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46005958318710327},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44408679008483887},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.43913161754608154},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.41168174147605896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4101274609565735}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8195387721061707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7672969102859497},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.547797441482544},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5406318306922913},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4953421652317047},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46005958318710327},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44408679008483887},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.43913161754608154},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.41168174147605896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4101274609565735},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2006-20","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-20","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6600000262260437,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1575829986","https://openalex.org/W2015143272","https://openalex.org/W2044222806","https://openalex.org/W2045660721","https://openalex.org/W2075076415","https://openalex.org/W2106603795","https://openalex.org/W2109349638","https://openalex.org/W2143855671","https://openalex.org/W2149425615","https://openalex.org/W2157906748"],"related_works":["https://openalex.org/W1547433061","https://openalex.org/W1840351222","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2074549717","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W1987011838","https://openalex.org/W2552102772"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,8,45,57,130],"speech":[4,14,28,36,155],"separation":[5],"system":[6],"as":[7,56],"front-end":[9],"processing":[10,127],"step":[11],"for":[12],"automatic":[13],"recognition":[15,108,151],"(ASR).":[16],"It":[17],"employs":[18],"computational":[19],"auditory":[20,41],"scene":[21],"analysis":[22],"(CASA)":[23],"to":[24,60,92,119],"separate":[25],"the":[26,30,34,51,62,66,106,114,121,125,145],"target":[27,63],"from":[29],"interference":[31],"speech.":[32,64],"Specifically,":[33],"mixed":[35],"is":[37,48,54,90],"preprocessed":[38],"based":[39,132],"on":[40],"peripheral":[42],"model.":[43],"Then":[44],"pitch":[46,53,160],"tracking":[47],"conducted":[49],"and":[50],"dominant":[52],"used":[55],"main":[58],"cue":[59],"find":[61],"Next,":[65],"time":[67],"frequency":[68],"(TF)":[69],"units":[70,162],"are":[71,78,102,117],"merged":[72],"into":[73,81,110],"many":[74],"segments.":[75],"These":[76],"segments":[77],"then":[79],"combined":[80],"streams":[82,95,116],"via":[83,96],"CASA":[84],"initial":[85],"grouping.":[86],"A":[87],"regrouping":[88],"strategy":[89],"employed":[91],"refine":[93],"these":[94],"amplitude":[97],"modulate":[98],"(AM)":[99],"cues,":[100],"which":[101],"finally":[103],"organized":[104],"by":[105,129],"speaker":[107,158],"techniques":[109],"corresponding":[111],"speakers.":[112],"Finally,":[113],"output":[115],"reconstructed":[118],"compensate":[120],"missing":[122],"data":[123],"in":[124],"abovementioned":[126],"steps":[128],"cluster":[131],"feature":[133],"reconstruction.":[134],"Experimental":[135],"results":[136],"of":[137],"ASR":[138],"show":[139],"that":[140],"at":[141],"low":[142],"TMR":[143],"(<-6dB)":[144],"proposed":[146],"method":[147],"offers":[148],"significantly":[149],"higher":[150],"accuracy.":[152],"Index":[153],"term:":[154],"separation,":[156],"CASA,":[157],"recognition,":[159],"tracking,":[161],"grouping,":[163],"reconstruction":[164]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}