{"id":"https://openalex.org/W4312941980","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892465","title":"LRTD: A Low-rank Transformer with Dynamic Depth and Width for Speech Recognition","display_name":"LRTD: A Low-rank Transformer with Dynamic Depth and Width for Speech Recognition","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312941980","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892465"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892465","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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/A5100616402","display_name":"Fan Yu","orcid":"https://orcid.org/0000-0002-4978-0023"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fan Yu","raw_affiliation_strings":["Xi'an Jiaotong University School of Computer Science&Technology,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University School of Computer Science&Technology,Xi'an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050052141","display_name":"Wei Xi","orcid":"https://orcid.org/0000-0001-9348-2982"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xi","raw_affiliation_strings":["Xi'an Jiaotong University School of Computer Science&Technology,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University School of Computer Science&Technology,Xi'an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100634648","display_name":"Zhao Yang","orcid":"https://orcid.org/0000-0001-7681-1473"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Yang","raw_affiliation_strings":["Xi'an Jiaotong University School of Computer Science&Technology,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University School of Computer Science&Technology,Xi'an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019637260","display_name":"Ziye Tong","orcid":"https://orcid.org/0000-0002-2910-196X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziye Tong","raw_affiliation_strings":["Xi'an Jiaotong University School of Computer Science&Technology,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University School of Computer Science&Technology,Xi'an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002809183","display_name":"Jingtong Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingtong Sun","raw_affiliation_strings":["Xi'an Jiaotong University School of Software Engineering,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University School of Software Engineering,Xi'an,China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100616402"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.1041,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.33227388,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9997000098228455,"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":0.9980999827384949,"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":0.7795937061309814},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7686151266098022},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5359208583831787},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5062035918235779},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43218696117401123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4124046564102173},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3939211070537567},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22000202536582947},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.2048431634902954},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10806331038475037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7795937061309814},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7686151266098022},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5359208583831787},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5062035918235779},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43218696117401123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4124046564102173},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3939211070537567},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22000202536582947},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.2048431634902954},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10806331038475037},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892465","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G1283425618","display_name":null,"funder_award_id":"2018AAA0101100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6986147707","display_name":null,"funder_award_id":"61832008,62072367","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1821462560","https://openalex.org/W1828163288","https://openalex.org/W1902934009","https://openalex.org/W2095705004","https://openalex.org/W2102113734","https://openalex.org/W2327501763","https://openalex.org/W2750499125","https://openalex.org/W2766219058","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2963242190","https://openalex.org/W2964233199","https://openalex.org/W2965116050","https://openalex.org/W2972470300","https://openalex.org/W2975381464","https://openalex.org/W2981857663","https://openalex.org/W2982479999","https://openalex.org/W2996428491","https://openalex.org/W3007122219","https://openalex.org/W3007227084","https://openalex.org/W3015286511","https://openalex.org/W3015720739","https://openalex.org/W3035030897","https://openalex.org/W3089604988","https://openalex.org/W3097777922","https://openalex.org/W3098985395","https://openalex.org/W3115511229","https://openalex.org/W4287667694","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6639703010","https://openalex.org/W6674330103","https://openalex.org/W6675365184","https://openalex.org/W6739901393","https://openalex.org/W6768021236","https://openalex.org/W6768080748"],"related_works":["https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W3098382480","https://openalex.org/W4287598411","https://openalex.org/W3100913109","https://openalex.org/W3198458223","https://openalex.org/W3126642501","https://openalex.org/W2964413124"],"abstract_inverted_index":{"Though":[0],"Transformer-based":[1],"models":[2],"have":[3],"achieved":[4],"great":[5],"success":[6],"in":[7,26],"the":[8,43,54,59,71,88,118,127,142],"automatic":[9],"speech":[10],"recognition":[11],"(ASR)":[12],"field,":[13],"they":[14],"are":[15],"generally":[16],"resource-hungry":[17],"and":[18,51,56,81,91],"computation-intensive":[19],"which":[20],"makes":[21],"them":[22],"difficult":[23],"to":[24,117],"deploy":[25],"resource-restricted":[27],"devices.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32,123],"propose":[33],"LRTD,":[34],"a":[35,132],"lightweight":[36],"Transformer":[37],"for":[38],"end-to-end":[39],"ASR.":[40],"LRTD":[41],"compresses":[42],"model":[44,61,73,101,114,143],"size":[45,144],"using":[46],"matrix":[47,128],"decomposition":[48,129],"during":[49],"training":[50],"further":[52],"reduces":[53],"depth":[55],"width":[57],"of":[58,70],"trained":[60],"dynamically":[62],"leveraging":[63],"two":[64,76,82,137],"structured":[65,78],"pruning":[66,138],"strategies.":[67],"The":[68,94],"performance":[69,105],"pruned":[72],"reply":[74],"on":[75,106],"additional":[77],"dropout":[79],"methods":[80,139],"search":[83],"techniques":[84],"that":[85,98,126],"can":[86,102,140],"recognize":[87],"important":[89],"layers":[90],"attention":[92],"heads.":[93],"experimental":[95],"results":[96],"show":[97],"our":[99],"proposed":[100],"achieve":[103],"competitive":[104],"Aishell-1":[107],"even":[108],"with":[109],"about":[110],"2.27":[111],"\u00d7":[112],"fewer":[113],"parameters":[115],"compared":[116],"baseline":[119],"transformer":[120],"model.":[121],"Moreover,":[122],"experimentally":[124],"demonstrate":[125],"technique":[130],"achieves":[131],"higher":[133],"compression":[134],"rate":[135],"while":[136],"adjust":[141],"flexibly.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}