{"id":"https://openalex.org/W112469173","doi":"https://doi.org/10.21437/eurospeech.2001-619","title":"Separating three simultaneous speeches with two microphones by integrating auditory and visual processing","display_name":"Separating three simultaneous speeches with two microphones by integrating auditory and visual processing","publication_year":2001,"publication_date":"2001-09-03","ids":{"openalex":"https://openalex.org/W112469173","doi":"https://doi.org/10.21437/eurospeech.2001-619","mag":"112469173"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2001-619","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","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/A5005141184","display_name":"Hiroshi G. Okuno","orcid":"https://orcid.org/0000-0002-8704-4318"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hiroshi G. Okuno","raw_affiliation_strings":["Kyoto University"],"affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091708408","display_name":"Kazuhiro Nakadai","orcid":"https://orcid.org/0000-0002-6134-4558"},"institutions":[{"id":"https://openalex.org/I4210086780","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19","country_code":"JP","type":"government","lineage":["https://openalex.org/I4210086780"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Nakadai","raw_affiliation_strings":["Japan Science and Technology Agency"],"affiliations":[{"raw_affiliation_string":"Japan Science and Technology Agency","institution_ids":["https://openalex.org/I4210086780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023670830","display_name":"Tino Lourens","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086780","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19","country_code":"JP","type":"government","lineage":["https://openalex.org/I4210086780"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tino Lourens","raw_affiliation_strings":["Japan Science and Technology Agency"],"affiliations":[{"raw_affiliation_string":"Japan Science and Technology Agency","institution_ids":["https://openalex.org/I4210086780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086835862","display_name":"Hiroaki Kitano","orcid":"https://orcid.org/0000-0002-3589-1953"},"institutions":[{"id":"https://openalex.org/I4210086780","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19","country_code":"JP","type":"government","lineage":["https://openalex.org/I4210086780"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroaki Kitano","raw_affiliation_strings":["Japan Science and Technology Agency"],"affiliations":[{"raw_affiliation_string":"Japan Science and Technology Agency","institution_ids":["https://openalex.org/I4210086780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005141184"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":1.8702,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84303627,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2643","last_page":"2646"},"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":0.9973000288009644,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6201445460319519},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5740907192230225},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5323840379714966},{"id":"https://openalex.org/keywords/interaural-time-difference","display_name":"Interaural time difference","score":0.4894062578678131},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.4834612309932709},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3856796622276306},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3618484437465668},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3296584486961365},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3021549582481384},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2837345004081726}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6201445460319519},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5740907192230225},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5323840379714966},{"id":"https://openalex.org/C103364767","wikidata":"https://www.wikidata.org/wiki/Q1807562","display_name":"Interaural time difference","level":3,"score":0.4894062578678131},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.4834612309932709},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3856796622276306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3618484437465668},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3296584486961365},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3021549582481384},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2837345004081726},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.2001-619","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W36769352","https://openalex.org/W43463692","https://openalex.org/W109581973","https://openalex.org/W198498694","https://openalex.org/W1525243411","https://openalex.org/W1567997379","https://openalex.org/W1597966709","https://openalex.org/W1990106150","https://openalex.org/W1998109441","https://openalex.org/W2046059186","https://openalex.org/W2114154451","https://openalex.org/W2129122669","https://openalex.org/W2139019327","https://openalex.org/W2169962852","https://openalex.org/W3132205412","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2112063689","https://openalex.org/W2292785222","https://openalex.org/W1606499391","https://openalex.org/W3133550200","https://openalex.org/W3135255973","https://openalex.org/W1985393731","https://openalex.org/W4317939968","https://openalex.org/W2089327421","https://openalex.org/W2071863156","https://openalex.org/W4390144857"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,23,38,48,85,88,98,105,130],"problem":[4],"of":[5,8,18,25,32,91,100,104,123,127,137],"automatic":[6],"recognition":[7,135],"three":[9,124],"simultaneous":[10,125],"speeches":[11,139],"with":[12],"two":[13],"microphones,":[14],"that":[15,17,31],"is,":[16],"sound":[19,26],"source":[20],"separation":[21],"where":[22],"number":[24],"sources":[27],"is":[28,37,42],"greater":[29],"than":[30],"microphones.":[33],"The":[34],"approach":[35],"used":[36],"direction-pass":[39],"filter,":[40],"which":[41],"implemented":[43],"by":[44,81,93,117],"hypothetical":[45],"reasoning":[46],"on":[47],"interaural":[49,54],"phase":[50],"difference":[51,56],"(IPD)":[52],"and":[53,62,67,73,96,110,133,142],"intensity":[55],"(IID).":[57],"Auditory":[58],"processing":[59],"calculates":[60,87],"IPD":[61,72],"IID":[63,74],"for":[64,70,75],"each":[65,101],"subband,":[66],"generates":[68],"hypotheses":[69],"precalculated":[71],"every":[76],"direction":[77,99,107],"including":[78],"one":[79],"obtained":[80],"visual":[82],"processing.":[83],"Then":[84],"system":[86],"belief":[89],"factor":[90],"hypothesis":[92],"Dempster-Shafer":[94],"theory":[95],"determines":[97],"subband.":[102],"Subbands":[103],"specific":[106],"are":[108,140],"collected":[109],"then":[111],"converted":[112],"to":[113],"a":[114],"wave":[115],"form":[116],"inverse":[118],"FFT.":[119],"With":[120],"200":[121],"benchmarks":[122],"utterances":[126],"Japanese":[128],"words,":[129],"average":[131],"1-best":[132],"10-best":[134],"rates":[136],"extracted":[138],"60%":[141],"81%,":[143],"respectively.":[144]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
