{"id":"https://openalex.org/W3197726142","doi":"https://doi.org/10.21437/interspeech.2021-819","title":"Extremely Low Footprint End-to-End ASR System for Smart Device","display_name":"Extremely Low Footprint End-to-End ASR System for Smart Device","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197726142","doi":"https://doi.org/10.21437/interspeech.2021-819","mag":"3197726142"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-819","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-819","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Extremely_low_footprint_end-to-end_ASR_system_for_smart_device/24217299","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024223042","display_name":"Zhifu Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifu Gao","raw_affiliation_strings":["Speech Lab, Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019176355","display_name":"Yiwu Yao","orcid":"https://orcid.org/0000-0003-4642-5840"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwu Yao","raw_affiliation_strings":["Platform of A. I., Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Platform of A. I., Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101777591","display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0002-9524-1602"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiliang Zhang","raw_affiliation_strings":["Speech Lab, Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114461997","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0002-4361-3195"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yang","raw_affiliation_strings":["Platform of A. I., Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Platform of A. I., Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058896884","display_name":"Ming Lei","orcid":"https://orcid.org/0000-0002-5712-3285"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Lei","raw_affiliation_strings":["Speech Lab, Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000620878","display_name":"Ian McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ian McLoughlin","raw_affiliation_strings":["ICT Cluster, Singapore Institute of Technology, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICT Cluster, Singapore Institute of Technology, Singapore","institution_ids":["https://openalex.org/I168639165"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4548","last_page":"4552"},"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":0.9984999895095825,"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":0.996399998664856,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8094046115875244},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.719983696937561},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5903661847114563},{"id":"https://openalex.org/keywords/end-user","display_name":"End user","score":0.5253217220306396},{"id":"https://openalex.org/keywords/end-user-development","display_name":"End-user development","score":0.4909351170063019},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.3238535523414612},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.22847875952720642},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15312761068344116},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10351863503456116},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06601971387863159}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8094046115875244},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.719983696937561},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5903661847114563},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.5253217220306396},{"id":"https://openalex.org/C2776867947","wikidata":"https://www.wikidata.org/wiki/Q500467","display_name":"End-user development","level":3,"score":0.4909351170063019},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.3238535523414612},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22847875952720642},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15312761068344116},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10351863503456116},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06601971387863159},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2021-819","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-819","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/24217299","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Extremely_low_footprint_end-to-end_ASR_system_for_smart_device/24217299","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/24217299","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Extremely_low_footprint_end-to-end_ASR_system_for_smart_device/24217299","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1810943226","https://openalex.org/W1828163288","https://openalex.org/W2133564696","https://openalex.org/W2327501763","https://openalex.org/W2605141709","https://openalex.org/W2739789140","https://openalex.org/W2889048668","https://openalex.org/W2889129739","https://openalex.org/W2894740066","https://openalex.org/W2916954108","https://openalex.org/W2936774411","https://openalex.org/W2953384591","https://openalex.org/W2962742956","https://openalex.org/W2963242190","https://openalex.org/W2963480671","https://openalex.org/W2965862774","https://openalex.org/W2972439411","https://openalex.org/W2972977747","https://openalex.org/W2981751377","https://openalex.org/W2996428491","https://openalex.org/W3015286511","https://openalex.org/W3015974384","https://openalex.org/W3033604713","https://openalex.org/W3034940165","https://openalex.org/W3078670009","https://openalex.org/W3097580812","https://openalex.org/W3162309234","https://openalex.org/W4294619417","https://openalex.org/W4297813615","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4299590256","https://openalex.org/W2919182614","https://openalex.org/W333503034","https://openalex.org/W3163634122","https://openalex.org/W3127005940","https://openalex.org/W2113114423","https://openalex.org/W4287122814","https://openalex.org/W2529145526","https://openalex.org/W2789393453","https://openalex.org/W4327633437"],"abstract_inverted_index":{"<p":[0],"dir=\"ltr\">Recently,":[1],"end-to-end":[2],"(E2E)":[3],"speech":[4],"recognition":[5,87],"has":[6],"become":[7],"popular,":[8],"since":[9],"it":[10],"can":[11],"integrate":[12],"the":[13,44,79,121,128,131,147],"acoustic,":[14],"pronunciation":[15],"and":[16,98,106,112,124],"language":[17],"models":[18,41],"into":[19],"a":[20,59],"single":[21],"neural":[22],"network,":[23],"which":[24],"outperforms":[25],"conventional":[26],"models.":[27],"Among":[28],"E2E":[29,71],"approaches,":[30],"attention-based":[31],"models,":[32],"e.g.":[33],"Transformer,":[34],"have":[35,42],"emerged":[36],"as":[37],"being":[38],"superior.":[39],"Such":[40],"opened":[43],"door":[45],"to":[46,77,94,108,144,158],"deployment":[47],"of":[48,62,81,149],"ASR":[49,72],"on":[50,120],"smart":[51,75],"devices,":[52,76],"however":[53],"they":[54],"still":[55],"suffer":[56],"from":[57,142,156],"requiring":[58],"large":[60],"number":[61],"model":[63,101],"parameters.":[64],"We":[65,89,116],"propose":[66],"an":[67],"extremely":[68],"low":[69],"footprint":[70],"system":[73],"for":[74],"achieve":[78],"goal":[80],"satisfying":[82],"resource":[83],"constraints":[84],"without":[85],"sacrificing":[86],"accuracy.":[88],"design":[90],"cross-layer":[91],"weight":[92],"sharing":[93],"improve":[95],"parameter":[96],"efficiency":[97],"further":[99],"exploit":[100],"compression":[102,138],"methods":[103],"including":[104],"sparsification":[105],"quantization,":[107],"reduce":[109],"memory":[110],"storage":[111],"boost":[113],"decoding":[114],"efficiency.":[115],"evaluate":[117],"our":[118],"approaches":[119],"public":[122],"AISHELL-1":[123],"AISHELL-2":[125,129],"benchmarks.":[126],"On":[127],"task,":[130],"proposed":[132],"method":[133],"achieves":[134],"more":[135],"than":[136],"10\u00d7":[137],"(model":[139],"size":[140],"reduces":[141,155],"248":[143],"24MB),":[145],"at":[146],"cost":[148],"only":[150],"minor":[151],"performance":[152],"loss":[153],"(CER":[154],"6.49%":[157],"6.92%).":[159]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
