{"id":"https://openalex.org/W3011795074","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023275","title":"Structure Growth for Small-Footprint Speech Recognition","display_name":"Structure Growth for Small-Footprint Speech Recognition","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011795074","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023275","mag":"3011795074"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023275","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/A5072245931","display_name":"Jiayao Wu","orcid":"https://orcid.org/0000-0002-5333-427X"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiayao Wu","raw_affiliation_strings":["School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056437232","display_name":"Zhiyuan Tang","orcid":"https://orcid.org/0000-0002-3786-7690"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Tang","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391494","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6992-7950"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072245931"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20626486,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"96","issue":null,"first_page":"461","last_page":"465"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.7794145345687866},{"id":"https://openalex.org/keywords/adaboost","display_name":"AdaBoost","score":0.7739795446395874},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.7617150545120239},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.745398759841919},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4903562068939209},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4860861599445343},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47498267889022827},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.471217542886734},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4608359932899475},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.44661328196525574},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3675331473350525},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.1723165214061737},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09922495484352112}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7794145345687866},{"id":"https://openalex.org/C141404830","wikidata":"https://www.wikidata.org/wiki/Q2823869","display_name":"AdaBoost","level":3,"score":0.7739795446395874},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.7617150545120239},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.745398759841919},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4903562068939209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4860861599445343},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47498267889022827},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.471217542886734},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4608359932899475},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.44661328196525574},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3675331473350525},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.1723165214061737},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09922495484352112},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023275","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1602122992","https://openalex.org/W1798945469","https://openalex.org/W1821462560","https://openalex.org/W1966280301","https://openalex.org/W2024490156","https://openalex.org/W2084910356","https://openalex.org/W2100404317","https://openalex.org/W2104364170","https://openalex.org/W2112076978","https://openalex.org/W2127141656","https://openalex.org/W2140285303","https://openalex.org/W2160815625","https://openalex.org/W2164921999","https://openalex.org/W2396813586","https://openalex.org/W2514741789","https://openalex.org/W2892258132","https://openalex.org/W2919115771","https://openalex.org/W2921194440","https://openalex.org/W2981022124","https://openalex.org/W4212883601","https://openalex.org/W4214673677","https://openalex.org/W6638060716","https://openalex.org/W6675460260","https://openalex.org/W6676769703","https://openalex.org/W6712551501"],"related_works":["https://openalex.org/W3039673966","https://openalex.org/W4293699968","https://openalex.org/W2002351707","https://openalex.org/W2035096001","https://openalex.org/W2327035729","https://openalex.org/W2923621274","https://openalex.org/W2101918547","https://openalex.org/W4312843811","https://openalex.org/W3112414093","https://openalex.org/W4210319752"],"abstract_inverted_index":{"Modern":[0],"speech":[1],"recognition":[2],"(ASR)":[3],"is":[4,40],"based":[5],"on":[6,19,127],"large-scale":[7],"deep":[8],"neural":[9],"nets":[10,108,121],"(DNNs)":[11],"with":[12],"various":[13],"architectures.":[14],"For":[15],"small-footprint":[16,55,129],"applications":[17],"running":[18],"low-power":[20],"chips,":[21],"however,":[22],"the":[23,26,45,96,102,139],"size":[24],"of":[25,51],"DNNs":[27],"must":[28],"be":[29],"extremely":[30],"constrained.":[31],"In":[32,68],"this":[33,69],"case,":[34],"training":[35],"a":[36,59,73,78,89,115,128],"generalizable":[37],"acoustic":[38,46],"model":[39],"not":[41],"feasible,":[42],"especially":[43],"when":[44],"conditions":[47],"are":[48],"diverse.":[49],"Most":[50],"existing":[52],"approaches":[53],"to":[54,91],"networks":[56],"start":[57,100],"from":[58,77,101],"large":[60],"net":[61,80,97],"and":[62,81,94,112,136,141,147],"reduce":[63],"its":[64],"scale":[65],"by":[66],"pruning.":[67],"paper,":[70],"we":[71],"investigate":[72],"reverse":[74],"idea:":[75],"starting":[76],"small":[79],"increasing":[82],"it":[83],"gradually.":[84,98],"This":[85],"structure-growth":[86],"approach":[87],"follows":[88],"`general":[90],"specific'":[92],"principle":[93],"grows":[95],"We":[99],"AdaBoost":[103,135],"algorithm":[104],"that":[105,118,133],"builds":[106,119],"specific":[107,120,123],"for":[109,122],"error-prone":[110],"data,":[111],"then":[113],"propose":[114],"new":[116],"ConBoost":[117,137,151],"conditions.":[124],"Our":[125],"experiments":[126],"ASR":[130],"task":[131],"demonstrated":[132],"both":[134],"outperform":[138],"baseline":[140],"other":[142],"comparative":[143],"methods":[144],"including":[145],"bagging":[146],"double-net":[148],"retraining.":[149],"Furthermore,":[150],"performs":[152],"better":[153],"than":[154],"AdaBoost.":[155]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}