{"id":"https://openalex.org/W3015595164","doi":"https://doi.org/10.1109/icassp40776.2020.9053967","title":"Attention-Based Gated Scaling Adaptive Acoustic Model for CTC-Based Speech Recognition","display_name":"Attention-Based Gated Scaling Adaptive Acoustic Model for CTC-Based Speech Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015595164","doi":"https://doi.org/10.1109/icassp40776.2020.9053967","mag":"3015595164"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053967","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5108267926","display_name":"Fenglin Ding","orcid":null},"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":"Fenglin Ding","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, 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, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","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, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"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":"Jun Du","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108267926"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.5302,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71707454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7404","last_page":"7408"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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":0.7925395369529724},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.7292688488960266},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6657739281654358},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5887434482574463},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5499545335769653},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5418627262115479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5132360458374023},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4909878075122833},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4858948588371277},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.47631368041038513},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4518754184246063},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4388979375362396},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4308403730392456},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2627127170562744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7925395369529724},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.7292688488960266},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6657739281654358},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5887434482574463},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5499545335769653},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5418627262115479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5132360458374023},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4909878075122833},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4858948588371277},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.47631368041038513},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4518754184246063},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4388979375362396},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4308403730392456},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2627127170562744},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053967","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W567546468","https://openalex.org/W1522301498","https://openalex.org/W1985371235","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2036351241","https://openalex.org/W2079623482","https://openalex.org/W2087006792","https://openalex.org/W2090320273","https://openalex.org/W2106051978","https://openalex.org/W2127141656","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2239847623","https://openalex.org/W2398776621","https://openalex.org/W2508162385","https://openalex.org/W2514740276","https://openalex.org/W2735006420","https://openalex.org/W2899771611","https://openalex.org/W2939164678","https://openalex.org/W2939173691","https://openalex.org/W2963242190","https://openalex.org/W2963403868","https://openalex.org/W2963596039","https://openalex.org/W2964121744","https://openalex.org/W3125118953","https://openalex.org/W4385245566","https://openalex.org/W6615969787","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W2145230572","https://openalex.org/W2166312020","https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W4401751953","https://openalex.org/W3133352777","https://openalex.org/W156567445","https://openalex.org/W3136989387","https://openalex.org/W2008737763"],"abstract_inverted_index":{"In":[0,29],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,91],"novel":[6],"adaptive":[7],"technique":[8],"that":[9],"uses":[10],"an":[11,44,55],"attention-based":[12],"gated":[13],"scaling":[14],"(AGS)":[15],"scheme":[16],"to":[17],"improve":[18],"deep":[19],"feature":[20],"learning":[21],"for":[22,119],"connectionist":[23],"temporal":[24],"classification":[25],"(CTC)":[26],"acoustic":[27],"modeling.":[28],"AGS,":[30],"the":[31,38,50,59,64,83,87,98,103,109,115,120],"outputs":[32],"of":[33,37,100],"each":[34],"hidden":[35],"layer":[36,52,62],"main":[39,65],"network":[40,66],"are":[41,67,114],"scaled":[42],"by":[43,53],"auxiliary":[45,60],"gate":[46],"matrix":[47],"extracted":[48],"from":[49],"lower":[51],"using":[54],"attention":[56],"mechanism.":[57],"Furthermore,":[58],"AGS":[61,89],"and":[63],"jointly":[68],"trained":[69],"without":[70],"requiring":[71],"second-pass":[72],"model":[73],"training":[74,107,112],"or":[75],"additional":[76],"speaker":[77],"information,":[78],"such":[79],"as":[80],"i-vector.":[81],"On":[82],"Mandarin":[84],"AISHELL-1":[85,111],"dataset,":[86],"proposed":[88],"yields":[90],"7.94%":[92],"character":[93],"error":[94],"rate":[95],"(CER).":[96],"To":[97],"best":[99,116],"our":[101],"knowledge,":[102],"results":[104],"obtained":[105],"when":[106],"on":[108],"full":[110],"set,":[113],"published":[117],"currently":[118],"end-to-end":[121],"systems.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}