{"id":"https://openalex.org/W2636483419","doi":"https://doi.org/10.1109/icassp.2017.7952160","title":"Deep long short-term memory adaptive beamforming networks for multichannel robust speech recognition","display_name":"Deep long short-term memory adaptive beamforming networks for multichannel robust speech recognition","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2636483419","doi":"https://doi.org/10.1109/icassp.2017.7952160","mag":"2636483419"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952160","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1711.08016","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101749753","display_name":"Zhong Meng","orcid":"https://orcid.org/0000-0001-7814-5929"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong Meng","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA","Mitsubishi Electric Research Laboratories, Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065994318","display_name":"Hakan Erdo\u011fan","orcid":"https://orcid.org/0000-0003-3140-8642"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hakan Erdogan","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":103,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"271","last_page":"275"},"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":0.9986000061035156,"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":0.9979000091552734,"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/beamforming","display_name":"Beamforming","score":0.8197673559188843},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7992596626281738},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7444943785667419},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.556939959526062},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.541473925113678},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5158318877220154},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47870612144470215},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.4512936770915985},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.4488428831100464},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4452122151851654},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4380953311920166},{"id":"https://openalex.org/keywords/adaptive-filter","display_name":"Adaptive filter","score":0.41423895955085754},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39871370792388916},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2524715065956116},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14655017852783203},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11620375514030457}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.8197673559188843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7992596626281738},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7444943785667419},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.556939959526062},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.541473925113678},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5158318877220154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47870612144470215},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.4512936770915985},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.4488428831100464},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4452122151851654},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4380953311920166},{"id":"https://openalex.org/C102248274","wikidata":"https://www.wikidata.org/wiki/Q168388","display_name":"Adaptive filter","level":2,"score":0.41423895955085754},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39871370792388916},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2524715065956116},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14655017852783203},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11620375514030457},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2017.7952160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952160","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"},{"id":"pmh:oai:arXiv.org:1711.08016","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.08016","pdf_url":"https://arxiv.org/pdf/1711.08016","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1711.08016","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.08016","pdf_url":"https://arxiv.org/pdf/1711.08016","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1482149378","https://openalex.org/W1524333225","https://openalex.org/W1935589317","https://openalex.org/W2005708641","https://openalex.org/W2009934439","https://openalex.org/W2060108923","https://openalex.org/W2061074721","https://openalex.org/W2063224314","https://openalex.org/W2064675550","https://openalex.org/W2091828388","https://openalex.org/W2115730999","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2148613904","https://openalex.org/W2158143227","https://openalex.org/W2160815625","https://openalex.org/W2288217446","https://openalex.org/W2289394825","https://openalex.org/W2289731793","https://openalex.org/W2293634267","https://openalex.org/W2398972335","https://openalex.org/W2402268235","https://openalex.org/W2407277936","https://openalex.org/W2506203739","https://openalex.org/W2517616541","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6713098461"],"related_works":["https://openalex.org/W2912153778","https://openalex.org/W2767070583","https://openalex.org/W4387163678","https://openalex.org/W4288108708","https://openalex.org/W2784052451","https://openalex.org/W2973430807","https://openalex.org/W4385280324","https://openalex.org/W2890685186","https://openalex.org/W2984436043","https://openalex.org/W4390245176"],"abstract_inverted_index":{"Far-field":[0],"speech":[1,25],"recognition":[2],"in":[3,75,105,113],"noisy":[4],"and":[5,30,65,70],"reverberant":[6],"conditions":[7],"remains":[8],"a":[9,24,42,76,91],"challenging":[10],"problem":[11,18],"despite":[12],"recent":[13],"deep":[14,92,107],"learning":[15],"breakthroughs.":[16],"This":[17],"is":[19,87],"commonly":[20],"addressed":[21],"by":[22],"acquiring":[23],"signal":[26],"from":[27],"multiple":[28],"microphones":[29,71],"performing":[31],"beamforming":[32,56,116,131],"over":[33,126],"them.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,101],"propose":[39],"to":[40,52,59,96,111],"use":[41,102],"recurrent":[43],"neural":[44],"network":[45],"with":[46,61,90,129],"long":[47],"short-term":[48],"memory":[49],"(LSTM)":[50],"architecture":[51],"adaptively":[53],"estimate":[54],"real-time":[55],"filter":[57,117],"coefficients":[58],"cope":[60],"non-stationary":[62],"environmental":[63],"noise":[64],"dynamic":[66],"nature":[67],"of":[68,78],"source":[69],"positions":[72],"which":[73],"results":[74],"set":[77],"timevarying":[79],"room":[80],"impulse":[81],"responses.":[82],"The":[83,119],"LSTM":[84,93,108],"adaptive":[85],"beamformer":[86],"jointly":[88],"trained":[89],"acoustic":[94,109],"model":[95,110],"predict":[97],"senone":[98],"labels.":[99],"Further,":[100],"hidden":[103],"units":[104],"the":[106,115],"assist":[112],"predicting":[114],"coefficients.":[118],"proposed":[120],"system":[121],"achieves":[122],"7.97%":[123],"absolute":[124],"gain":[125],"baseline":[127],"systems":[128],"no":[130],"on":[132],"CHiME-3":[133],"real":[134],"evaluation":[135],"set.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2017-06-30T00:00:00"}