{"id":"https://openalex.org/W4296068756","doi":"https://doi.org/10.21437/interspeech.2022-915","title":"A Multi-level Acoustic Feature Extraction Framework for Transformer Based End-to-End Speech Recognition","display_name":"A Multi-level Acoustic Feature Extraction Framework for Transformer Based End-to-End Speech Recognition","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296068756","doi":"https://doi.org/10.21437/interspeech.2022-915"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-915","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-915","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100364802","display_name":"Jin Li","orcid":"https://orcid.org/0000-0002-6131-456X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210115303","display_name":"Moscow University \u00abSynergy\u00bb","ror":"https://ror.org/028mtfb17","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210115303"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN","RU"],"is_corresponding":false,"raw_author_name":"Jin Li","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China,","Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems,","CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China,","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems,","institution_ids":[]},{"raw_affiliation_string":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems,","institution_ids":["https://openalex.org/I4210115303"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036142381","display_name":"Rongfeng Su","orcid":"https://orcid.org/0000-0002-7228-5768"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210115303","display_name":"Moscow University \u00abSynergy\u00bb","ror":"https://ror.org/028mtfb17","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210115303"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN","RU"],"is_corresponding":false,"raw_author_name":"Rongfeng Su","raw_affiliation_strings":["CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems,","Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China,","Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems,","institution_ids":["https://openalex.org/I4210115303"]},{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China,","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035857878","display_name":"Xurong Xie","orcid":"https://orcid.org/0000-0002-6714-6296"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210115303","display_name":"Moscow University \u00abSynergy\u00bb","ror":"https://ror.org/028mtfb17","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210115303"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN","RU"],"is_corresponding":false,"raw_author_name":"Xurong Xie","raw_affiliation_strings":["Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems,","Institute of Software, Chinese Academy of Sciences, Beijing, China","Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China,","CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems,","institution_ids":[]},{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China,","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"raw_affiliation_string":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems,","institution_ids":["https://openalex.org/I4210115303"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363636","display_name":"Lan Wang","orcid":"https://orcid.org/0000-0001-7925-7957"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210115303","display_name":"Moscow University \u00abSynergy\u00bb","ror":"https://ror.org/028mtfb17","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210115303"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN","RU"],"is_corresponding":false,"raw_author_name":"Lan Wang","raw_affiliation_strings":["Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems,","CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems,","Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems,","institution_ids":[]},{"raw_affiliation_string":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems,","institution_ids":["https://openalex.org/I4210115303"]},{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China,","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100608121","display_name":"Nan Yan","orcid":"https://orcid.org/0000-0001-6729-2448"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210115303","display_name":"Moscow University \u00abSynergy\u00bb","ror":"https://ror.org/028mtfb17","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210115303"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN","RU"],"is_corresponding":false,"raw_author_name":"Nan Yan","raw_affiliation_strings":["Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems,","Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China,","CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems,","institution_ids":[]},{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China,","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"raw_affiliation_string":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems,","institution_ids":["https://openalex.org/I4210115303"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3173","last_page":"3177"},"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":0.9973999857902527,"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":0.9972000122070312,"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":0.7374778985977173},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7353343963623047},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6294799447059631},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6271059513092041},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6210328936576843},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.42591604590415955},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3783891201019287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3294696807861328},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3132745027542114},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16119733452796936},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09939995408058167},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07119449973106384}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7374778985977173},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7353343963623047},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6294799447059631},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6271059513092041},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6210328936576843},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.42591604590415955},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3783891201019287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3294696807861328},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3132745027542114},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16119733452796936},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09939995408058167},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07119449973106384}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-915","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-915","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1031871451","display_name":null,"funder_award_id":"NSFC U1736202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2003507557","display_name":null,"funder_award_id":"NSFC 61771461","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G257170","display_name":null,"funder_award_id":"U1736202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6143720773","display_name":null,"funder_award_id":"62106255","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6611988724","display_name":"\u65e9\u671f\u963f\u5c14\u8328\u6d77\u9ed8\u75c7\u7684\u8a00\u8bed\u7279\u5f81\u53d8\u5f02\u6027\u53ca\u5176\u795e\u7ecf\u673a\u5236\u7814\u7a76","funder_award_id":"61771461","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1526236009","https://openalex.org/W1875842236","https://openalex.org/W2101234009","https://openalex.org/W2193413348","https://openalex.org/W2514741789","https://openalex.org/W2892009249","https://openalex.org/W2895807593","https://openalex.org/W2900092534","https://openalex.org/W2913718171","https://openalex.org/W2944255943","https://openalex.org/W2962780374","https://openalex.org/W2963091558","https://openalex.org/W2963163009","https://openalex.org/W2972389417","https://openalex.org/W3015457435","https://openalex.org/W3015960524","https://openalex.org/W3016167541","https://openalex.org/W3133764785","https://openalex.org/W3144345593","https://openalex.org/W3152221657","https://openalex.org/W3160207687","https://openalex.org/W3161873870","https://openalex.org/W3198871389","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3126788496","https://openalex.org/W2916997151","https://openalex.org/W3198455051","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W642007152","https://openalex.org/W2122233706","https://openalex.org/W2105439218","https://openalex.org/W3143423642","https://openalex.org/W2131711534"],"abstract_inverted_index":{"Transformer":[0,75,156],"based":[1,76,136],"end-to-end":[2],"modelling":[3],"approaches":[4,26],"with":[5,24,74,88,95],"multiple":[6],"stream":[7,35,87,94,99,120],"inputs":[8],"have":[9,37],"been":[10],"achieved":[11],"great":[12],"success":[13],"in":[14],"various":[15],"automatic":[16],"speech":[17,184],"recognition":[18,185],"(ASR)":[19],"tasks.An":[20],"important":[21],"issue":[22],"associated":[23],"such":[25,48],"is":[27,43,100,108,121,139],"that":[28,69,107],"the":[29,50,111,118,131,146,155,160,178],"intermediate":[30],"features":[31,106,128,144],"derived":[32],"from":[33],"each":[34],"might":[36],"similar":[38],"representations":[39],"and":[40,91,148,151,173,182],"thus":[41],"it":[42],"lacking":[44],"of":[45,81,113,171],"feature":[46,66,132,134,164],"diversity,":[47],"as":[49],"descriptions":[51],"related":[52],"to":[53,102,123,141],"speaker":[54],"characteristics.To":[55],"address":[56],"this":[57,59],"issue,":[58],"paper":[60],"proposed":[61,161],"a":[62,85,92],"novel":[63],"multi-level":[64,162],"acoustic":[65,163],"extraction":[67,165],"framework":[68,79],"can":[70],"be":[71],"easily":[72],"combined":[73],"ASR":[77],"models.The":[78],"consists":[80],"two":[82],"input":[83],"streams:":[84],"shallow":[86,98,105],"high-resolution":[89],"spectrograms":[90],"deep":[93,119,127],"low-resolution":[96],"spectrograms.The":[97],"used":[101,122,140],"acquire":[103],"traditional":[104],"beneficial":[109],"for":[110,129],"classification":[112],"phones":[114],"or":[115],"words":[116],"while":[117],"obtain":[124],"utterance-level":[125],"speaker-invariant":[126],"improving":[130],"diversity.A":[133],"correlation":[135],"fusion":[137],"strategy":[138],"aggregate":[142],"both":[143],"across":[145],"frequency":[147],"time":[149],"domains":[150],"then":[152],"fed":[153],"into":[154],"encoder-decoder":[157],"module.By":[158],"using":[159],"framework,":[166],"state-of-the-art":[167],"word":[168],"error":[169],"rate":[170],"21.7%":[172],"2.5%":[174],"were":[175],"obtained":[176],"on":[177],"HKUST":[179],"Mandarin":[180],"telephone":[181],"Librispeech":[183],"tasks":[186],"respectively.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}