{"id":"https://openalex.org/W2937641152","doi":"https://doi.org/10.1109/icassp.2019.8683620","title":"Learning Efficient Sparse Structures in Speech Recognition","display_name":"Learning Efficient Sparse Structures in Speech Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2937641152","doi":"https://doi.org/10.1109/icassp.2019.8683620","mag":"2937641152"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5008931958","display_name":"Jingchi Zhang","orcid":"https://orcid.org/0009-0009-4412-7103"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jingchi Zhang","raw_affiliation_strings":["Duke University, Durham, North Carolina, USA"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, North Carolina, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104667051","display_name":"Wei Wen","orcid":"https://orcid.org/0000-0002-5485-0372"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Wen","raw_affiliation_strings":["Duke University, Durham, North Carolina, USA"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, North Carolina, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064741703","display_name":"Michael Deisher","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Deisher","raw_affiliation_strings":["Intel Corporation, Hillsboro, Oregon, USA"],"affiliations":[{"raw_affiliation_string":"Intel Corporation, Hillsboro, Oregon, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103877341","display_name":"Hsin-Pai Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hsin-Pai Cheng","raw_affiliation_strings":["Duke University, Durham, North Carolina, USA"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, North Carolina, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100429403","display_name":"Hai Li","orcid":"https://orcid.org/0000-0003-3228-6544"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hai Li","raw_affiliation_strings":["Duke University, Durham, North Carolina, USA"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, North Carolina, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058073627","display_name":"Yiran Chen","orcid":"https://orcid.org/0000-0002-1486-8412"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiran Chen","raw_affiliation_strings":["Duke University, Durham, North Carolina, USA"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, North Carolina, USA","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5008931958"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":0.5601,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74006611,"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":"2717","last_page":"2721"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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":0.822358250617981},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6573689579963684},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6085411310195923},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5616508722305298},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5568422675132751},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5464486479759216},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5224327445030212},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5097872614860535},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5017869472503662},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4609878659248352},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.4533213973045349},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4362446367740631},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.423764705657959},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34704333543777466},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2559114694595337},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21076899766921997}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.822358250617981},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6573689579963684},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6085411310195923},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5616508722305298},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5568422675132751},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5464486479759216},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5224327445030212},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5097872614860535},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5017869472503662},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4609878659248352},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.4533213973045349},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4362446367740631},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.423764705657959},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34704333543777466},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2559114694595337},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21076899766921997},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1935978687","https://openalex.org/W2005708641","https://openalex.org/W2143612262","https://openalex.org/W2251321385","https://openalex.org/W2293634267","https://openalex.org/W2503931548","https://openalex.org/W2603326847","https://openalex.org/W2608554408","https://openalex.org/W2754526845","https://openalex.org/W2785540404","https://openalex.org/W2963000224","https://openalex.org/W2963674932","https://openalex.org/W4297689207","https://openalex.org/W6631362777","https://openalex.org/W6638632666","https://openalex.org/W6691770337","https://openalex.org/W6696934422","https://openalex.org/W6725543821","https://openalex.org/W6736780897","https://openalex.org/W6744208968","https://openalex.org/W6747599758"],"related_works":["https://openalex.org/W2160451571","https://openalex.org/W2495256954","https://openalex.org/W1566315437","https://openalex.org/W2259317772","https://openalex.org/W2594897229","https://openalex.org/W4221142855","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W4290708361","https://openalex.org/W2244609359"],"abstract_inverted_index":{"Recurrent":[0],"neural":[1],"networks":[2],"(RNNs),":[3],"especially":[4],"long":[5],"short-term":[6],"memories":[7],"(LSTMs)":[8],"have":[9],"been":[10],"widely":[11],"used":[12],"in":[13,53,77,121,147],"speech":[14,54],"recognition":[15],"and":[16,33,91,107,116],"natural":[17],"language":[18],"processing.":[19],"As":[20],"the":[21,30,35,69,83,100,114,118,122,148,154],"sizes":[22],"of":[23],"RNN":[24],"models":[25],"grow":[26],"for":[27,50],"better":[28],"performance,":[29],"computation":[31],"cost":[32],"therefore":[34],"required":[36],"hardware":[37],"resource":[38],"increase":[39],"rapidly.":[40],"We":[41,124],"propose":[42],"an":[43],"efficient":[44],"structural":[45,94],"sparsity":[46],"(ESS)":[47],"learning":[48],"method":[49,87,128],"acoustic":[51],"modeling":[52],"recognition.":[55],"ESS":[56,127,141],"aims":[57],"to":[58],"generate":[59],"a":[60,93],"model":[61,96,115,132],"that":[62,140],"offers":[63],"higher":[64],"execution":[65],"efficiency":[66],"while":[67],"maintaining":[68],"accuracy.":[70],"A":[71],"three-step":[72],"training":[73,89],"pipeline":[74],"is":[75],"developed":[76],"our":[78,126],"work.":[79],"First,":[80],"we":[81,112],"apply":[82],"group":[84],"Lasso":[85],"regularization":[86],"during":[88],"process":[90],"learn":[92],"sparse":[95,102],"from":[97],"scratch.":[98],"Then":[99],"learned":[101],"structures":[103],"will":[104],"be":[105,109],"fixed":[106],"cannot":[108],"changed.":[110],"Finally,":[111],"retrain":[113],"update":[117],"nonzero":[119],"parameters":[120],"model.":[123],"applied":[125],"on":[129,133],"classic":[130],"HMM+LSTM":[131],"Kaldi":[134],"toolkit.":[135],"The":[136],"experimental":[137],"results":[138],"show":[139],"can":[142],"remove":[143],"72.5%":[144],"weight":[145,149],"groups":[146],"matrices":[150],"when":[151],"slightly":[152],"increasing":[153],"word":[155],"error":[156],"rate":[157],"(WER)":[158],"1.1%.":[159]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}