{"id":"https://openalex.org/W2641525828","doi":"https://doi.org/10.1109/icassp.2017.7953142","title":"Unsupervised utterance-wise beamformer estimation with speech recognition-level criterion","display_name":"Unsupervised utterance-wise beamformer estimation with speech recognition-level criterion","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2641525828","doi":"https://doi.org/10.1109/icassp.2017.7953142","mag":"2641525828"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953142","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953142","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/A5101768343","display_name":"Takuya Higuchi","orcid":"https://orcid.org/0000-0002-0361-7132"},"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":"Takuya Higuchi","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"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":"Takuya Yoshioka","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"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":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation","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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5170","last_page":"5174"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9948999881744385,"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/computer-science","display_name":"Computer science","score":0.7441270351409912},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7078945636749268},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.6886602640151978},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6765986084938049},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.49910640716552734},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4750392735004425},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44891366362571716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4413626194000244},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41411587595939636},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21502956748008728},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07472923398017883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7441270351409912},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7078945636749268},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.6886602640151978},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6765986084938049},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.49910640716552734},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4750392735004425},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44891366362571716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4413626194000244},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41411587595939636},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21502956748008728},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07472923398017883},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953142","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953142","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W330298975","https://openalex.org/W1513862252","https://openalex.org/W1995562189","https://openalex.org/W2003203076","https://openalex.org/W2010362084","https://openalex.org/W2033310064","https://openalex.org/W2046317813","https://openalex.org/W2094147890","https://openalex.org/W2160306971","https://openalex.org/W2185726469","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2398042854","https://openalex.org/W2398972335","https://openalex.org/W2400339399","https://openalex.org/W2407277936","https://openalex.org/W2514488347","https://openalex.org/W4256161595","https://openalex.org/W6607333740","https://openalex.org/W6651134346","https://openalex.org/W6686651311","https://openalex.org/W6713176261","https://openalex.org/W6743356167"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W818226659","https://openalex.org/W2940588515","https://openalex.org/W2996333928","https://openalex.org/W2009075871","https://openalex.org/W1909151225","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840"],"abstract_inverted_index":{"In":[0],"this":[1,157],"paper,":[2],"we":[3,124,135],"perform":[4],"beamforming":[5,63],"with":[6,64,74,106,129,186],"a":[7,55,65,84,95,107,183,187],"speech":[8,52,66,108],"recognition-level":[9,67,109],"criterion.":[10,68,110,189],"A":[11],"beamformer":[12,24,44,101,138,160,181,184],"is":[13,45],"usually":[14],"designed":[15,185],"by":[16,21,28,78],"optimizing":[17],"signal-level":[18,35,188],"criteria,":[19],"e.g.,":[20],"minimizing":[22],"the":[23,30,42,46,100,144,148],"output":[25],"covariance":[26],"or":[27],"maximizing":[29],"signal-to-noise":[31],"ratio":[32],"(SNR).":[33],"Such":[34],"criteria":[36],"do":[37],"not":[38],"always":[39],"guarantee":[40],"that":[41,179],"optimized":[43],"best":[47],"for":[48,61,98,102,172],"noise":[49],"robust":[50],"automatic":[51],"recognition.":[53],"Recently,":[54],"few":[56],"approaches":[57,70],"have":[58],"been":[59],"proposed":[60],"performing":[62],"These":[69],"train":[71],"beamformers":[72],"along":[73],"an":[75,113,130],"acoustic":[76,115],"model":[77,116,168],"using":[79,139],"multichannel":[80],"training":[81],"data":[82],"and":[83,89,133,152],"parallel":[85],"corpus":[86],"of":[87],"noisy":[88],"clean":[90],"data.":[91],"This":[92],"paper":[93],"proposes":[94],"novel":[96],"approach":[97],"estimating":[99],"every":[103,173],"test":[104,174],"utterance":[105],"We":[111],"use":[112],"unsupervised":[114],"adaptation":[117],"scheme":[118],"to":[119,142,164],"optimize":[120,136],"our":[121,137,159,180],"beamformer.":[122],"Specifically,":[123],"first":[125],"obtain":[126],"decoding":[127,150],"results":[128,151,177],"initialized":[131],"beamformer,":[132],"then":[134],"back":[140],"propagation":[141],"minimize":[143],"cross":[145],"entropy":[146],"between":[147],"first-pass":[149],"actual":[153],"network":[154],"outputs.":[155],"With":[156],"approach,":[158],"can":[161],"be":[162],"trained":[163],"discriminate":[165],"hidden":[166],"Markov":[167],"states":[169],"more":[170],"clearly":[171],"utterance.":[175],"Experimental":[176],"show":[178],"outperforms":[182]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}