{"id":"https://openalex.org/W4388820532","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317482","title":"Modified Parametric Multichannel Wiener Filter for Low-latency Enhancement of Speech Mixtures with Unknown Number of Speakers","display_name":"Modified Parametric Multichannel Wiener Filter for Low-latency Enhancement of Speech Mixtures with Unknown Number of Speakers","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820532","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317482"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317482","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5039052970","display_name":"Ning Guo","orcid":"https://orcid.org/0000-0002-0829-7262"},"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"]},{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["DE","JP"],"is_corresponding":true,"raw_author_name":"Ning Guo","raw_affiliation_strings":["NTT Corporation,Japan","International Audio Laboratories Erlangen, Germany","NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"International Audio Laboratories Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Araki","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076091643","display_name":"Takehiro Moriya","orcid":"https://orcid.org/0000-0003-4591-1273"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takehiro Moriya","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5039052970"],"corresponding_institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I4210123192"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16235839,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1042","last_page":"1049"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973999857902527,"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/speech-enhancement","display_name":"Speech enhancement","score":0.794689953327179},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.7020506858825684},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6627156734466553},{"id":"https://openalex.org/keywords/wiener-filter","display_name":"Wiener filter","score":0.6413787007331848},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6233385801315308},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5782421231269836},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4554232954978943},{"id":"https://openalex.org/keywords/finite-impulse-response","display_name":"Finite impulse response","score":0.41957178711891174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22159209847450256},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21927660703659058},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1688767671585083},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16741305589675903},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1244966983795166},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.06228750944137573}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.794689953327179},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.7020506858825684},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6627156734466553},{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.6413787007331848},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6233385801315308},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5782421231269836},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4554232954978943},{"id":"https://openalex.org/C198386975","wikidata":"https://www.wikidata.org/wiki/Q117785","display_name":"Finite impulse response","level":2,"score":0.41957178711891174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22159209847450256},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21927660703659058},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1688767671585083},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16741305589675903},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1244966983795166},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.06228750944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317482","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":29,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W653761051","https://openalex.org/W1965255698","https://openalex.org/W1976805820","https://openalex.org/W1978752674","https://openalex.org/W1987906574","https://openalex.org/W2024059910","https://openalex.org/W2042860487","https://openalex.org/W2060108923","https://openalex.org/W2106272332","https://openalex.org/W2121141823","https://openalex.org/W2127365717","https://openalex.org/W2144404214","https://openalex.org/W2147665979","https://openalex.org/W2155638623","https://openalex.org/W2158143227","https://openalex.org/W2159284737","https://openalex.org/W2168729028","https://openalex.org/W2398042854","https://openalex.org/W2403555780","https://openalex.org/W2587603783","https://openalex.org/W2798582127","https://openalex.org/W2972728246","https://openalex.org/W2997688633","https://openalex.org/W3047232705","https://openalex.org/W3093410526","https://openalex.org/W4206231176","https://openalex.org/W4232859291","https://openalex.org/W6735168207"],"related_works":["https://openalex.org/W2106793170","https://openalex.org/W1577562165","https://openalex.org/W1562344721","https://openalex.org/W2028846388","https://openalex.org/W4295210860","https://openalex.org/W2072015625","https://openalex.org/W2117955483","https://openalex.org/W2161534637","https://openalex.org/W2010870899","https://openalex.org/W3168171120"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,43,99,112],"novel":[4],"low-latency":[5,78],"online":[6],"beamforming":[7],"(BF)":[8],"algorithm":[9],"called":[10],"the":[11,54,59,65,68,83,88,118,121,131],"Modified":[12],"Parametric":[13,101],"Multichannel":[14,102],"Wiener":[15,103],"Filter":[16,104],"(Mod-PMWF),":[17],"which":[18],"enhances":[19,116],"speech":[20,44,50],"mixtures":[21],"with":[22],"unknown":[23],"and":[24,58,139],"varying":[25],"number":[26,55],"of":[27,56,85],"speakers.":[28],"Although":[29],"such":[30,49],"conventional":[31,100],"BFs":[32,38,86],"as":[33,53],"Linearly":[34],"Constrained":[35],"Minimum":[36],"Variance":[37],"(LCMV":[39],"BFs)":[40],"can":[41,109],"enhance":[42],"mixture,":[45],"they":[46],"typically":[47],"require":[48],"mixture":[51,71,122],"attributes":[52,72],"speakers":[57,66,119],"acoustic":[60],"transfer":[61],"functions":[62],"(ATFs)":[63],"from":[64],"to":[67,87],"microphones.":[69],"When":[70],"are":[73],"unavailable,":[74],"estimating":[75,125],"them":[76],"by":[77,97],"processing":[79],"is":[80],"challenging,":[81],"hindering":[82],"application":[84],"problem.":[89],"In":[90],"this":[91,95],"paper,":[92],"we":[93],"overcome":[94],"problem":[96],"modifying":[98],"(PMWF).":[105],"The":[106],"proposed":[107,132],"Mod-PMWF":[108],"adaptively":[110],"form":[111],"directivity":[113],"pattern":[114],"that":[115],"all":[117],"in":[120,135],"without":[123],"explicitly":[124],"these":[126],"attributes.":[127],"Our":[128],"experiments":[129],"show":[130],"BF\u2019s":[133],"effectiveness":[134],"interference":[136],"reduction":[137],"ratios":[138],"subjective":[140],"listening":[141],"tests.":[142]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}