{"id":"https://openalex.org/W4408356255","doi":"https://doi.org/10.1109/icassp49660.2025.10887865","title":"EffectiveASR: A Single-Step Non-Autoregressive Mandarin Speech Recognition Architecture with High Accuracy and Inference Speed","display_name":"EffectiveASR: A Single-Step Non-Autoregressive Mandarin Speech Recognition Architecture with High Accuracy and Inference Speed","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356255","doi":"https://doi.org/10.1109/icassp49660.2025.10887865"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5088311121","display_name":"Ziyang Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyang Zhuang","raw_affiliation_strings":["Ping An Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093993569","display_name":"Chenfeng Miao","orcid":"https://orcid.org/0009-0006-1986-3035"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Chenfeng Miao","raw_affiliation_strings":["Ping An Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101570585","display_name":"Kun Zou","orcid":"https://orcid.org/0009-0008-0575-5142"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Zou","raw_affiliation_strings":["Ping An Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080919889","display_name":"Ming Fang","orcid":"https://orcid.org/0000-0003-1932-2037"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Fang","raw_affiliation_strings":["Ping An Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012261926","display_name":"Tao Wei","orcid":"https://orcid.org/0000-0002-6549-3999"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Wei","raw_affiliation_strings":["Ping An Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406497","display_name":"Zijian Li","orcid":"https://orcid.org/0000-0002-3964-3789"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zijian Li","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101977180","display_name":"Ning Cheng","orcid":"https://orcid.org/0000-0002-0988-5023"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Cheng","raw_affiliation_strings":["Ping An Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014243317","display_name":"Wei Hu","orcid":"https://orcid.org/0000-0001-7754-1858"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Hu","raw_affiliation_strings":["Ping An Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702012","display_name":"Shaojun Wang","orcid":"https://orcid.org/0000-0002-3680-9464"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Shaojun Wang","raw_affiliation_strings":["Ping An Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"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":0.9955000281333923,"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":0.9955000281333923,"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":0.9817000031471252,"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":0.7808517217636108},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.737853467464447},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7232195734977722},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7211452722549438},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6976511478424072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.53031986951828},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.47955843806266785},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37943363189697266},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3369895815849304},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1428019404411316},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11837679147720337},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0702696442604065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7808517217636108},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.737853467464447},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7232195734977722},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7211452722549438},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6976511478424072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.53031986951828},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.47955843806266785},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37943363189697266},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3369895815849304},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1428019404411316},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11837679147720337},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0702696442604065},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":32,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2327501763","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963242190","https://openalex.org/W2988975212","https://openalex.org/W3016167541","https://openalex.org/W3097777922","https://openalex.org/W3097874139","https://openalex.org/W3097882114","https://openalex.org/W3112157188","https://openalex.org/W3160622492","https://openalex.org/W3162249256","https://openalex.org/W3162431424","https://openalex.org/W3162899666","https://openalex.org/W3164692279","https://openalex.org/W3197140813","https://openalex.org/W3198259287","https://openalex.org/W4224931714","https://openalex.org/W4283067311","https://openalex.org/W4297841485","https://openalex.org/W4361990931","https://openalex.org/W4385822407","https://openalex.org/W4392902949","https://openalex.org/W4402111392","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6739901393","https://openalex.org/W6754473786","https://openalex.org/W6787300339","https://openalex.org/W6792627859"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2366752344"],"abstract_inverted_index":{"Non-autoregressive":[0],"(NAR)":[1],"automatic":[2],"speech":[3],"recognition":[4],"(ASR)":[5],"models":[6,28],"predict":[7],"tokens":[8],"independently":[9],"and":[10,48,68,100],"simultaneously,":[11],"bringing":[12],"high":[13,46],"inference":[14,49,131],"speed.":[15],"However,":[16],"there":[17],"is":[18],"still":[19],"a":[20,40],"gap":[21],"in":[22],"the":[23,26,31,74,98,106,119,125],"accuracy":[24,47],"of":[25,116],"NAR":[27,42],"compared":[29,104],"to":[30,63,72,105],"autoregressive":[32],"(AR)":[33],"models.":[34,108],"In":[35],"this":[36],"paper,":[37],"we":[38],"propose":[39],"single-step":[41],"ASR":[43],"architecture":[44],"with":[45,84,88,128],"speed,":[50],"called":[51],"EffectiveASR.":[52],"It":[53,78],"uses":[54],"an":[55,69],"Index":[56],"Mapping":[57],"Vector":[58],"(IMV)":[59],"based":[60],"alignment":[61,70,89],"generator":[62],"generate":[64],"alignments":[65,75],"during":[66],"training,":[67],"predictor":[71],"learn":[73],"for":[76],"inference.":[77],"can":[79],"be":[80],"trained":[81],"end-to-end":[82],"(E2E)":[83],"cross-entropy":[85],"loss":[86],"combined":[87],"loss.":[90],"The":[91],"proposed":[92],"EffectiveASR":[93],"achieves":[94,111],"competitive":[95],"results":[96],"on":[97,118],"AISHELL-1":[99,120],"AISHELL-2":[101],"Mandarin":[102],"benchmarks":[103],"leading":[107],"Specifically,":[109],"it":[110],"character":[112],"error":[113],"rates":[114],"(CER)":[115],"4.26%/4.62%":[117],"dev/test":[121],"dataset,":[122],"which":[123],"outperforms":[124],"AR":[126],"Conformer":[127],"about":[129],"30x":[130],"speedup.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}