{"id":"https://openalex.org/W3011384584","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023043","title":"Learning Adaptive Downsampling Encoding for Online End-to-End Speech Recognition","display_name":"Learning Adaptive Downsampling Encoding for Online End-to-End Speech Recognition","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011384584","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023043","mag":"3011384584"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023043","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/A5086118002","display_name":"Rui Na","orcid":"https://orcid.org/0000-0002-4675-4786"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rui Na","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101505189","display_name":"Junfeng Hou","orcid":"https://orcid.org/0000-0003-3635-5332"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfeng Hou","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038369085","display_name":"Wu Guo","orcid":"https://orcid.org/0000-0002-3779-7944"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Guo","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381758","display_name":"Yan Song","orcid":"https://orcid.org/0000-0002-5668-9068"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Song","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lirong Dai","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5086118002"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.1443,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61912389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"5","issue":null,"first_page":"850","last_page":"854"},"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":0.9988999962806702,"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":0.9919999837875366,"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/upsampling","display_name":"Upsampling","score":0.9336556196212769},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8018593192100525},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6343886852264404},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6139174103736877},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.577433705329895},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.547060489654541},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5291063189506531},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.44949105381965637},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4424450099468231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3648553490638733},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.31188514828681946}],"concepts":[{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.9336556196212769},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8018593192100525},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6343886852264404},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6139174103736877},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.577433705329895},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.547060489654541},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5291063189506531},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.44949105381965637},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4424450099468231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3648553490638733},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31188514828681946},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023043","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"},{"id":"mag:3041700925","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002284007591682","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1489125746","https://openalex.org/W1524333225","https://openalex.org/W1855892484","https://openalex.org/W2010291496","https://openalex.org/W2024490156","https://openalex.org/W2108682071","https://openalex.org/W2133564696","https://openalex.org/W2152205330","https://openalex.org/W2271840356","https://openalex.org/W2396384435","https://openalex.org/W2605141709","https://openalex.org/W2799800213","https://openalex.org/W2890297197","https://openalex.org/W2949975180","https://openalex.org/W2962826786","https://openalex.org/W6623517193","https://openalex.org/W6629052376","https://openalex.org/W6631362777","https://openalex.org/W6639156005","https://openalex.org/W6676023451","https://openalex.org/W6679434410","https://openalex.org/W6735706088"],"related_works":["https://openalex.org/W2062399876","https://openalex.org/W2607795551","https://openalex.org/W3155117723","https://openalex.org/W1991429770","https://openalex.org/W1983892167","https://openalex.org/W2281134365","https://openalex.org/W4310746709","https://openalex.org/W1950940422","https://openalex.org/W2129146436","https://openalex.org/W2032507829"],"abstract_inverted_index":{"Attention":[0],"based":[1],"encoder-decoder":[2],"models":[3],"have":[4],"shown":[5],"promising":[6],"performance":[7],"for":[8,13,103],"various":[9],"sequence-to-sequence":[10],"problems.":[11],"However,":[12],"speech":[14,20,106],"recognition,":[15],"the":[16,36,47,54,71,90,135,139],"very":[17],"long":[18],"input":[19,37,72,97],"consumes":[21],"a":[22,64,75],"lot":[23],"of":[24,57,126],"computation":[25,48],"and":[26,32,82,100],"memory":[27],"resource":[28],"when":[29],"performing":[30],"encoding":[31,137],"soft":[33],"attention":[34],"over":[35],"sequence.":[38],"While":[39],"fixed-rate":[40],"downsampling":[41,67,92,131],"is":[42,101],"usually":[43],"employed":[44],"to":[45,52,142],"reduce":[46,115],"steps,":[49],"it":[50],"fails":[51],"consider":[53],"variable":[55,143],"durations":[56],"phonemes.":[58],"Motivated":[59],"by":[60,78,120],"this,":[61],"we":[62],"propose":[63],"differentiable":[65],"adaptive":[66,136],"approach":[68,93],"which":[69],"encodes":[70],"sequence":[73],"with":[74,129],"recurrent":[76],"layer":[77],"keeping":[79],"crucial":[80],"frames":[81,85],"discarding":[83],"redundant":[84],"adaptively":[86],"in":[87],"real-time.":[88],"Therefore,":[89],"proposed":[91,112],"can":[94,114],"dynamically":[95],"generate":[96],"hidden":[98],"representations":[99],"suitable":[102],"online":[104],"end-to-end":[105],"recognition.":[107],"Experiments":[108],"show":[109],"that":[110],"our":[111],"method":[113],"phone":[116],"error":[117],"rate":[118],"(PER)":[119],"7.0":[121],"%":[122],"relative":[123],"without":[124],"loss":[125],"speed":[127,144],"compared":[128],"fixed":[130],"technique.":[132],"In":[133],"addition,":[134],"makes":[138],"model":[140],"robust":[141],"speech.":[145]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}