{"id":"https://openalex.org/W2922439870","doi":"https://doi.org/10.23919/apsipa.2018.8659564","title":"Online LSTM-based Iterative Mask Estimation for Multi-Channel Speech Enhancement and ASR","display_name":"Online LSTM-based Iterative Mask Estimation for Multi-Channel Speech Enhancement and ASR","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2922439870","doi":"https://doi.org/10.23919/apsipa.2018.8659564","mag":"2922439870"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659564","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5049067709","display_name":"Yan-Hui Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yan-Hui Tu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101642220","display_name":"Nan Zhou","orcid":"https://orcid.org/0000-0003-0925-7729"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Zhou","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, Georgia, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5049067709"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.6606,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71325333,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"362","last_page":"366"},"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":0.9987999796867371,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9958999752998352,"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/pesq","display_name":"PESQ","score":0.9868960380554199},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7971354722976685},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7621439099311829},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6945369839668274},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5671141147613525},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.4327571392059326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42066675424575806},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.301961749792099},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.071692556142807}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.9868960380554199},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7971354722976685},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7621439099311829},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6945369839668274},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5671141147613525},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.4327571392059326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42066675424575806},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.301961749792099},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.071692556142807},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659564","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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":35,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1591801644","https://openalex.org/W1598508708","https://openalex.org/W1602032261","https://openalex.org/W1897240248","https://openalex.org/W1934041838","https://openalex.org/W1978752674","https://openalex.org/W1993882792","https://openalex.org/W2002342963","https://openalex.org/W2046869671","https://openalex.org/W2060108923","https://openalex.org/W2087774313","https://openalex.org/W2121767183","https://openalex.org/W2131342762","https://openalex.org/W2134642725","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2289394825","https://openalex.org/W2289480995","https://openalex.org/W2345067732","https://openalex.org/W2400339399","https://openalex.org/W2408744528","https://openalex.org/W2476521382","https://openalex.org/W2559260703","https://openalex.org/W2586584460","https://openalex.org/W2589857635","https://openalex.org/W2749337587","https://openalex.org/W2767071179","https://openalex.org/W2785517859","https://openalex.org/W6607333740","https://openalex.org/W6635900476","https://openalex.org/W6679429981","https://openalex.org/W6713176261","https://openalex.org/W6730321509","https://openalex.org/W6743444209"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W2342810974","https://openalex.org/W3016109656","https://openalex.org/W2513767140","https://openalex.org/W1973895194","https://openalex.org/W3135613579","https://openalex.org/W4388016426","https://openalex.org/W1980687383","https://openalex.org/W2037635165","https://openalex.org/W4200562864"],"abstract_inverted_index":{"Accurate":[0],"steering":[1,31],"vector":[2],"estimation":[3,52],"is":[4,39,142,184],"the":[5,13,18,30,57,67,88,105,123,156,162,168,193,210,216,221],"key":[6],"point":[7],"for":[8,36,70,95,112,137],"a":[9,37,128,138,226],"beamformer":[10],"which":[11,28,118,183],"suppresses":[12],"background":[14],"noise":[15],"to":[16,55,122,147,175,181,186,205],"improve":[17,56,87,167],"noisy":[19],"speech":[20,89,97,114],"quality":[21,90],"and":[22,65,92,116,177],"intelligibility.":[23],"Recently,":[24],"time-frequency":[25],"masking":[26],"approach,":[27,224],"estimates":[29],"vectors":[32],"that":[33,83,161,215],"are":[34],"utilized":[35],"beamformer,":[38],"popular":[40],"in":[41,73,78,152],"this":[42,100],"field.":[43],"In":[44,99,126],"particular,":[45],"we":[46,80,102],"have":[47],"proposed":[48],"an":[49,199],"iterative":[50],"mask":[51],"(IME)":[53],"approach":[54,219],"complex":[58],"Gaussian":[59],"mixture":[60],"model":[61],"(CGMM)":[62],"based":[63,195],"beamforming":[64],"yield":[66],"best":[68],"system":[69],"multi-channel":[71,96,113],"ASR":[72],"CHiME-4":[74,157,211],"challenge":[75],"[1].":[76],"And":[77,207],"[2],":[79],"also":[81],"demonstrated":[82],"our":[84,109],"algorithm":[85,111,165],"could":[86],"(PESQ)":[91],"intelligibility":[93],"(STOI)":[94],"enhancement.":[98],"study,":[101],"focus":[103],"on":[104,155,209],"online":[106,163,217,222],"processing":[107],"of":[108,232],"IME":[110,164,218],"enhancement":[115,169],"ASR,":[117],"achieves":[119],"comparable":[120,185],"performance":[121],"offline":[124,190],"version.":[125],"addition,":[127],"regression":[129],"long":[130],"short-term":[131],"memory":[132],"recurrent":[133],"neural":[134],"network":[135],"(LSTM-RNN)":[136],"multiple-target":[139],"joint":[140],"learning":[141],"utilized,":[143],"denoted":[144],"as":[145],"LSTM-MT,":[146],"replace":[148],"two":[149],"separate":[150],"models":[151],"[2].":[153],"Experiments":[154],"simulation":[158],"data":[159,213],"show":[160,214],"can":[166,197],"performance,":[170],"e.g.,":[171],"PESQ":[172,201],"from":[173,179,203],"2.18":[174],"2.58":[176,204],"STOI":[178],"86.85":[180],"94.51,":[182],"those":[187],"obtained":[188],"by":[189],"IME.":[191],"Furthermore,":[192],"LSTM-MT":[194],"post-processing":[196],"achieve":[198],"additional":[200],"improvement":[202],"2.71.":[206],"experiments":[208],"real":[212],"outperforms":[220],"CGMM-based":[223],"with":[225],"relative":[227],"word":[228],"error":[229],"reduction":[230],"(WER)":[231],"14.49%.":[233]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}