{"id":"https://openalex.org/W3097829404","doi":"https://doi.org/10.21437/interspeech.2020-2556","title":"Self-and-Mixed Attention Decoder with Deep Acoustic Structure for Transformer-Based LVCSR","display_name":"Self-and-Mixed Attention Decoder with Deep Acoustic Structure for Transformer-Based LVCSR","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097829404","doi":"https://doi.org/10.21437/interspeech.2020-2556","mag":"3097829404"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2556","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2556","pdf_url":"https://www.isca-archive.org/interspeech_2020/zhou20i_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2020/zhou20i_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102864167","display_name":"Xinyuan Zhou","orcid":"https://orcid.org/0000-0003-2815-8857"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Xinyuan Zhou","raw_affiliation_strings":["Shanghai Normal University, Shanghai, China","National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056020864","display_name":"Grandee Lee","orcid":"https://orcid.org/0000-0001-9603-5141"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Grandee Lee","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004568334","display_name":"Emre Y\u0131lmaz","orcid":"https://orcid.org/0000-0001-7466-3358"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Emre Y\u0131lmaz","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056415893","display_name":"Yanhua Long","orcid":"https://orcid.org/0000-0003-0924-408X"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhua Long","raw_affiliation_strings":["Shanghai Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110832899","display_name":"Jiaen Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaen Liang","raw_affiliation_strings":["Unisound AI Technology Co., Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co., Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2165,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.800861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5016","last_page":"5020"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7308691740036011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7141594886779785},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.51935875415802},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.18458712100982666},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10387727618217468},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08424505591392517}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7308691740036011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7141594886779785},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.51935875415802},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.18458712100982666},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10387727618217468},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08424505591392517}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2556","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2556","pdf_url":"https://www.isca-archive.org/interspeech_2020/zhou20i_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2020-2556","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2556","pdf_url":"https://www.isca-archive.org/interspeech_2020/zhou20i_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7376540038","display_name":null,"funder_award_id":"61701306","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320698","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3097829404.pdf","grobid_xml":"https://content.openalex.org/works/W3097829404.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1586532344","https://openalex.org/W1899504021","https://openalex.org/W2130942839","https://openalex.org/W2183341477","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2530876040","https://openalex.org/W2577366047","https://openalex.org/W2766219058","https://openalex.org/W2886180730","https://openalex.org/W2890964657","https://openalex.org/W2892009249","https://openalex.org/W2936078256","https://openalex.org/W2939111082","https://openalex.org/W2962780374","https://openalex.org/W2962826786","https://openalex.org/W2963240019","https://openalex.org/W2963242190","https://openalex.org/W2963850025","https://openalex.org/W2964302946","https://openalex.org/W2972389417","https://openalex.org/W2972451902","https://openalex.org/W2972555663","https://openalex.org/W2972778435","https://openalex.org/W2972818416","https://openalex.org/W2976556660","https://openalex.org/W2985287635","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Transformer":[0],"has":[1],"shown":[2],"impressive":[3],"performance":[4],"in":[5,99],"automatic":[6],"speech":[7],"recognition.It":[8],"uses":[9],"an":[10],"encoder-decoder":[11],"structure":[12,37,49,70,112],"with":[13,45],"self-attention":[14,62],"to":[15,51,64,136],"learn":[16,65],"the":[17,53,85,110,118,124,129,137],"relationship":[18],"between":[19,87],"high-level":[20],"representation":[21,55],"of":[22,27,56,74,90,115,139],"source":[23],"inputs":[24],"and":[25,93,121],"embedding":[26,102],"target":[28],"outputs.In":[29],"this":[30,134],"paper,":[31],"we":[32,59],"propose":[33],"a":[34,40,46,61,66,79,100],"novel":[35],"decoder":[36,43],"that":[38,83,109],"features":[39],"self-and-mixed":[41],"attention":[42,81],"(SMAD)":[44],"deep":[47,68],"acoustic":[48,54,69,75,91],"(DAS)":[50],"improve":[52],"Transformer-based":[57],"LVCSR.Specifically,":[58],"introduce":[60],"mechanism":[63,82],"multi-layer":[67],"for":[71],"multiple":[72],"levels":[73,89],"abstraction.We":[76],"also":[77],"design":[78],"mixed":[80],"learns":[84],"alignment":[86],"different":[88],"abstraction":[92],"its":[94],"corresponding":[95],"linguistic":[96],"information":[97],"simultaneously":[98],"shared":[101],"space.The":[103],"ASR":[104],"experiments":[105],"on":[106,117,123,133],"Aishell-1":[107],"show":[108],"proposed":[111],"achieves":[113],"CERs":[114],"4.8%":[116],"dev":[119],"set":[120],"5.1%":[122],"test":[125],"set,":[126],"which":[127],"are":[128],"best":[130,138],"reported":[131],"results":[132],"task":[135],"our":[140],"knowledge.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}