{"id":"https://openalex.org/W3012476642","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023287","title":"Teacher-Student BLSTM Mask Model for Robust Acoustic Beamforming","display_name":"Teacher-Student BLSTM Mask Model for Robust Acoustic Beamforming","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3012476642","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023287","mag":"3012476642"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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/A5057325055","display_name":"Zhaoyi Liu","orcid":"https://orcid.org/0000-0003-0697-9080"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhaoyi Liu","raw_affiliation_strings":["Peking University Shenzhen Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002795838","display_name":"Yuexian Zou","orcid":"https://orcid.org/0000-0001-9999-6140"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexian Zou","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5057325055"],"corresponding_institution_ids":["https://openalex.org/I4210128628"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20087149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"638","last_page":"643"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.7815524339675903},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7006658315658569},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6206105947494507},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5763782858848572},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5538705587387085},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.492664635181427},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4769134223461151},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47168830037117004},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4523792862892151},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.413221150636673},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3738653361797333},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10087299346923828},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07816383242607117}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7815524339675903},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7006658315658569},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6206105947494507},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5763782858848572},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5538705587387085},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.492664635181427},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4769134223461151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47168830037117004},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4523792862892151},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.413221150636673},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3738653361797333},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10087299346923828},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07816383242607117},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1821462560","https://openalex.org/W1978752674","https://openalex.org/W1981706894","https://openalex.org/W2069681747","https://openalex.org/W2147207799","https://openalex.org/W2148613904","https://openalex.org/W2288645994","https://openalex.org/W2398042854","https://openalex.org/W2559260703","https://openalex.org/W2559809918","https://openalex.org/W2568308529","https://openalex.org/W2718052359","https://openalex.org/W2735006420","https://openalex.org/W2749337587","https://openalex.org/W2889801373","https://openalex.org/W2897248861","https://openalex.org/W2962866211","https://openalex.org/W2963376890","https://openalex.org/W2963458655","https://openalex.org/W6631362777","https://openalex.org/W6638523607"],"related_works":["https://openalex.org/W2896203542","https://openalex.org/W201299990","https://openalex.org/W876328409","https://openalex.org/W4319068615","https://openalex.org/W4214946933","https://openalex.org/W1879255185","https://openalex.org/W2148473678","https://openalex.org/W3004719695","https://openalex.org/W2120442551","https://openalex.org/W2769861442"],"abstract_inverted_index":{"Microphone":[0],"array":[1],"beamforming":[2],"has":[3],"been":[4],"approved":[5],"to":[6,117,163,194,251],"be":[7,110],"an":[8],"effective":[9],"approach":[10],"for":[11,22,41,53,169,220],"suppressing":[12],"adverse":[13],"interferences.":[14],"Recently,":[15],"acoustic":[16],"beamformers":[17],"employing":[18],"neural":[19],"networks":[20],"(NN)":[21],"time-frequency":[23],"(T-F)":[24],"mask":[25,59,98,120,141,146,151,167,187,198,206,213,236],"prediction,":[26],"termed":[27],"as":[28,38,138,217],"Mask-BF,":[29],"have":[30],"received":[31],"tremendous":[32],"interest":[33],"and":[34,143,158,172,180],"shown":[35],"great":[36],"benefits":[37],"a":[39,78,139,144,201,203,218],"front-end":[40],"distant":[42],"automatic":[43],"speech":[44],"recognition":[45],"(ASR).":[46],"However,":[47],"our":[48,234],"preliminary":[49],"experiments":[50],"using":[51],"Mask-BF":[52,254],"ASR":[54,221],"task":[55],"show":[56,228],"that":[57,105,229],"the":[58,69,74,90,93,97,106,114,119,165,177,181,190,196,223,230,252,256],"model":[60,121,142,152],"trained":[61,154],"with":[62,113,155,184],"only":[63],"simulated":[64,115,156,171,178],"training":[65,192],"data":[66,71,79,94,108,116,125,174,179,183,193],"underperforms":[67],"when":[68],"real-recording":[70,107,173,182,257],"appears":[72],"in":[73,255],"testing":[75],"stage,":[76],"where":[77,240],"mismatch":[80,95,126],"problem":[81],"occurs.":[82],"In":[83],"this":[84],"study,":[85],"we":[86,241],"aim":[87],"at":[88],"reducing":[89],"impact":[91],"of":[92,233],"on":[96,222],"model.":[99,199],"Our":[100,211],"research":[101],"is":[102,153,160,208,215,238],"quite":[103],"intuitive":[104],"can":[109],"used":[111],"together":[112],"make":[118],"more":[122],"robust":[123],"against":[124],"problem.":[127],"Specifically,":[128],"two":[129],"bi-directional":[130],"long":[131],"short-term":[132],"memory":[133],"(BLSTM)":[134],"models,":[135],"are":[136],"designed":[137],"teacher":[140,150],"student":[145,197],"model,":[147],"respectively.":[148],"The":[149],"data,":[157],"it":[159],"then":[161],"employed":[162],"generate":[164],"soft":[166,186],"labels":[168,188],"both":[170],"separately.":[175],"Then,":[176],"generated":[185],"form":[189],"new":[191],"train":[195],"As":[200],"result,":[202],"novel":[204],"T-S":[205,212,235],"BF":[207,214,237],"developed":[209],"accordingly.":[210],"evaluated":[216],"frontend":[219],"CHiME-3":[224],"dataset.":[225],"Experimental":[226],"results":[227],"generalization":[231],"ability":[232],"enhanced":[239],"obtain":[242],"relative":[243],"4%":[244],"word":[245],"error":[246],"rate":[247],"(WER)":[248],"reduction":[249],"compared":[250],"baseline":[253],"test":[258],"set.":[259]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}