{"id":"https://openalex.org/W3133709295","doi":"https://doi.org/10.1109/iscslp49672.2021.9362055","title":"Improving Attention-based End-to-end ASR by Incorporating an N-gram Neural Network","display_name":"Improving Attention-based End-to-end ASR by Incorporating an N-gram Neural Network","publication_year":2021,"publication_date":"2021-01-24","ids":{"openalex":"https://openalex.org/W3133709295","doi":"https://doi.org/10.1109/iscslp49672.2021.9362055","mag":"3133709295"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp49672.2021.9362055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5077069016","display_name":"Junyi Ao","orcid":"https://orcid.org/0000-0001-8979-0835"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junyi Ao","raw_affiliation_strings":["Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038062913","display_name":"Tom Ko","orcid":"https://orcid.org/0000-0002-5324-8961"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tom Ko","raw_affiliation_strings":["Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5077069016"],"corresponding_institution_ids":["https://openalex.org/I3045169105"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02912811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"1","last_page":"5"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.927216649055481},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7449965476989746},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5569926500320435},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5349937677383423},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.5219033360481262},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5170934200286865},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5031189322471619},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4998037815093994},{"id":"https://openalex.org/keywords/gram","display_name":"Gram","score":0.4797157645225525},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.44725093245506287},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4213118553161621},{"id":"https://openalex.org/keywords/end-user","display_name":"End user","score":0.42043113708496094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4164540767669678}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.927216649055481},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7449965476989746},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5569926500320435},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5349937677383423},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.5219033360481262},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5170934200286865},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5031189322471619},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4998037815093994},{"id":"https://openalex.org/C161369605","wikidata":"https://www.wikidata.org/wiki/Q41803","display_name":"Gram","level":3,"score":0.4797157645225525},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.44725093245506287},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4213118553161621},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.42043113708496094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4164540767669678},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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":1,"locations":[{"id":"doi:10.1109/iscslp49672.2021.9362055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W179875071","https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1586532344","https://openalex.org/W1614298861","https://openalex.org/W1686810756","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W2005708641","https://openalex.org/W2058695628","https://openalex.org/W2064675550","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2171928131","https://openalex.org/W2185726469","https://openalex.org/W2193413348","https://openalex.org/W2289003027","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2526425061","https://openalex.org/W2696967604","https://openalex.org/W2766219058","https://openalex.org/W2802201485","https://openalex.org/W2888779557","https://openalex.org/W2889028433","https://openalex.org/W2950577311","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963240019","https://openalex.org/W2964308564","https://openalex.org/W2998704965","https://openalex.org/W3015208154","https://openalex.org/W4285719527","https://openalex.org/W6600284362","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6635078382","https://openalex.org/W6636510571","https://openalex.org/W6637373629","https://openalex.org/W6638749077","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6680532216","https://openalex.org/W6687566353","https://openalex.org/W6713762819"],"related_works":["https://openalex.org/W2906970013","https://openalex.org/W3126081632","https://openalex.org/W2625039379","https://openalex.org/W2088254117","https://openalex.org/W4299590256","https://openalex.org/W4254593385","https://openalex.org/W2790582133","https://openalex.org/W2250909759","https://openalex.org/W1901380241","https://openalex.org/W2532616038"],"abstract_inverted_index":{"In":[0,120],"attention-based":[1,135],"end-to-end":[2,57,87,118,136],"ASR,":[3],"the":[4,15,19,25,38,42,53,56,60,63,70,82,86,91,108,117,132,144,160,163,168,172],"intrinsic":[5,26,83],"LM":[6,27,84],"is":[7,28,34,47],"modeled":[8],"by":[9,166],"an":[10,66,112],"RNN":[11,97],"and":[12,59,96,146],"it":[13,33,46],"forms":[14],"major":[16],"part":[17],"of":[18,55,65,72,80,85,110,127,134,162,171],"decoder.":[20],"Comparing":[21],"with":[22,37,41,187],"external":[23,61,67],"LMs,":[24],"considered":[29],"as":[30,32],"modest":[31],"only":[35,188],"trained":[36],"transcription":[39],"associated":[40],"speech":[43],"data.":[44],"Although":[45],"a":[48,156,189],"common":[49],"practise":[50],"to":[51,106,158],"interpolate":[52],"scores":[54],"model":[58,68,193],"LM,":[62],"need":[64],"hurts":[69],"novelty":[71],"end-to-end.":[73],"Therefore,":[74],"researchers":[75],"are":[76],"investigating":[77],"different":[78],"ways":[79],"improving":[81],"model.":[88,119],"By":[89],"observing":[90],"fact":[92],"that":[93,140,180],"N-gram":[94,113,128,164],"LMs":[95,98],"can":[99],"complement":[100],"each":[101],"other,":[102],"we":[103,123],"would":[104],"like":[105],"investigate":[107],"effect":[109],"implementing":[111],"neural":[114,129],"network":[115,130],"inside":[116],"this":[121],"paper,":[122],"examine":[124],"two":[125],"implementations":[126,142],"in":[131,192],"context":[133],"ASR.":[137],"We":[138,153],"find":[139],"both":[141],"improve":[143],"baseline":[145],"CBOW":[147],"(Continuous":[148],"Bag-of-Words)":[149],"performs":[150],"slightly":[151],"better.":[152],"further":[154],"propose":[155],"way":[157],"minimize":[159],"size":[161],"component":[165],"utilizing":[167],"coda":[169],"information":[170],"modeling":[173],"units.":[174],"Experiments":[175],"on":[176],"LibriSpeech":[177],"dataset":[178],"show":[179],"our":[181],"proposed":[182],"method":[183],"achieves":[184],"obvious":[185],"improvement":[186],"slight":[190],"increase":[191],"parameters.":[194]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}