{"id":"https://openalex.org/W2714509385","doi":"https://doi.org/10.1109/icassp.2017.7952242","title":"Probabilistic spatial dictionary based online adaptive beamforming for meeting recognition in noisy and reverberant environments","display_name":"Probabilistic spatial dictionary based online adaptive beamforming for meeting recognition in noisy and reverberant environments","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2714509385","doi":"https://doi.org/10.1109/icassp.2017.7952242","mag":"2714509385"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101438174","display_name":"Nobutaka Ito","orcid":"https://orcid.org/0000-0001-9740-6848"},"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":"Nobutaka Ito","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, 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 Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"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":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","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 Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"681","last_page":"685"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9965999722480774,"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/beamforming","display_name":"Beamforming","score":0.895281195640564},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.8694767951965332},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7800536155700684},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7269529104232788},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.634148895740509},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.6209208965301514},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.587604820728302},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.49078473448753357},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.42672258615493774},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4201662242412567},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.413247287273407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.405434250831604},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.24247336387634277},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.20433512330055237},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.16481974720954895},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13150843977928162}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.895281195640564},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8694767951965332},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7800536155700684},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7269529104232788},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.634148895740509},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.6209208965301514},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.587604820728302},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.49078473448753357},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.42672258615493774},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4201662242412567},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.413247287273407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.405434250831604},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.24247336387634277},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.20433512330055237},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.16481974720954895},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13150843977928162},{"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:10.1109/icassp.2017.7952242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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":31,"referenced_works":["https://openalex.org/W1558643924","https://openalex.org/W1934041838","https://openalex.org/W1981463705","https://openalex.org/W1987906574","https://openalex.org/W2005733316","https://openalex.org/W2009153891","https://openalex.org/W2012910847","https://openalex.org/W2018205510","https://openalex.org/W2031583051","https://openalex.org/W2043216213","https://openalex.org/W2081074144","https://openalex.org/W2129171989","https://openalex.org/W2145167175","https://openalex.org/W2146146065","https://openalex.org/W2153773386","https://openalex.org/W2167546860","https://openalex.org/W2167689159","https://openalex.org/W2171784699","https://openalex.org/W2213768793","https://openalex.org/W2288645994","https://openalex.org/W2394967684","https://openalex.org/W2402583539","https://openalex.org/W2465697055","https://openalex.org/W2536165811","https://openalex.org/W3141933106","https://openalex.org/W4285719527","https://openalex.org/W6633348054","https://openalex.org/W6651792828","https://openalex.org/W6681537870","https://openalex.org/W6711908631","https://openalex.org/W6719417910"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W2037265366","https://openalex.org/W2026603686","https://openalex.org/W2767070583","https://openalex.org/W2784052451","https://openalex.org/W2348931051","https://openalex.org/W2962707588","https://openalex.org/W2118992737"],"abstract_inverted_index":{"Here":[0],"we":[1,72,100],"propose":[2],"online":[3],"adaptive":[4],"beamforming":[5,42,135,162],"for":[6,119,134],"automatic":[7],"speech":[8],"recognition":[9],"(ASR)":[10],"in":[11,13,27,46,48,80,138],"meetings":[12,47,79],"noisy,":[14],"reverberant":[15],"environments.":[16],"The":[17,143],"proposed":[18,144],"method":[19,145],"is":[20],"based":[21],"on":[22,152],"recently":[23],"developed":[24],"mask-based":[25,41],"beamforming,":[26],"which":[28],"accurate":[29,44],"mask":[30,130],"estimation":[31,131],"and":[32,51,61,83,91,132],"diarization":[33,133],"are":[34],"paramount.":[35],"Real-world":[36],"experiments":[37],"have":[38],"shown":[39],"that":[40,108],"enables":[43,126],"ASR":[45],"small":[49],"noise":[50,82],"reverberation":[52,63,84],"with":[53,74,85],"a":[54,62,75,102,106,111],"signal-to-noise":[55],"ratio":[56],"(SNR)":[57],"of":[58,66,88,94,110,115],"15\u201325":[59],"dB":[60,90],"time":[64],"(RT)":[65],"120\u2013350":[67],"ms.":[68,96],"In":[69],"this":[70,98],"paper,":[71],"deal":[73],"more":[76],"adverse":[77,141],"condition:":[78],"large":[81],"an":[86,92],"SNR":[87],"3\u201315":[89],"RT":[93],"500":[95],"To":[97],"end,":[99],"exploit":[101],"probabilistic":[103],"spatial":[104],"dictionary,":[105],"dictionary":[107,125],"consists":[109],"pre-trained":[112],"probability":[113],"distribution":[114],"source":[116],"location":[117],"features":[118],"each":[120],"potential":[121],"speaker":[122],"location.":[123],"This":[124],"us":[127],"to":[128,159],"perform":[129],"accurately,":[136],"even":[137],"the":[139,147],"above":[140],"condition.":[142],"reduced":[146],"word":[148],"error":[149],"rate":[150],"(WER)":[151],"real":[153],"meeting":[154],"data":[155],"by":[156],"54.8%":[157],"relative":[158],"our":[160],"previous":[161],"method.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}