{"id":"https://openalex.org/W4405303369","doi":"https://doi.org/10.1109/lsp.2024.3516700","title":"Hypformer: A Fast Hypothesis-Driven Rescoring Speech Recognition Framework","display_name":"Hypformer: A Fast Hypothesis-Driven Rescoring Speech Recognition Framework","publication_year":2024,"publication_date":"2024-12-12","ids":{"openalex":"https://openalex.org/W4405303369","doi":"https://doi.org/10.1109/lsp.2024.3516700"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3516700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3516700","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5044255594","display_name":"Xuyi Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuyi Zhuang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China","Harbin Institute of Technology (Shenzhen) in Shenzhen, Guangdon, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen) in Shenzhen, Guangdon, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073118994","display_name":"Yukun Qian","orcid":"https://orcid.org/0000-0001-9095-4024"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yukun Qian","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China","Harbin Institute of Technology (Shenzhen) in Shenzhen, Guangdon, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen) in Shenzhen, Guangdon, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009651653","display_name":"Mingjiang Wang","orcid":"https://orcid.org/0000-0002-4706-009X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjiang Wang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China","Harbin Institute of Technology (Shenzhen) in Shenzhen, Guangdon, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen) in Shenzhen, Guangdon, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5044255594"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20513499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"471","last_page":"475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9947999715805054,"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":0.9947999715805054,"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":0.9865999817848206,"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":0.9585999846458435,"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":0.7524530291557312},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6622087955474854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3953370749950409}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7524530291557312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6622087955474854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3953370749950409}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2024.3516700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3516700","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1265899161","display_name":null,"funder_award_id":"62176102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1828714495","display_name":null,"funder_award_id":"2020B1515120004","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G3929901318","display_name":null,"funder_award_id":"62276076","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"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2766219058","https://openalex.org/W2963242190","https://openalex.org/W2963434219","https://openalex.org/W2988975212","https://openalex.org/W3015286511","https://openalex.org/W3015686596","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/W3162431424","https://openalex.org/W3162899666","https://openalex.org/W3164692279","https://openalex.org/W3196500669","https://openalex.org/W3197304116","https://openalex.org/W3197478142","https://openalex.org/W3198259287","https://openalex.org/W3200006799","https://openalex.org/W4212772209","https://openalex.org/W4221151577","https://openalex.org/W4221167707","https://openalex.org/W4283067311","https://openalex.org/W4385245566","https://openalex.org/W4385822407","https://openalex.org/W6746208923","https://openalex.org/W6754473786","https://openalex.org/W6792627859","https://openalex.org/W6803401863","https://openalex.org/W6873560614"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Recently,":[0],"the":[1,70,81,99],"performance":[2,88],"of":[3,65,93],"non-autoregressive":[4,59],"ASR":[5,87],"models":[6],"has":[7],"made":[8],"significant":[9],"progress":[10],"but":[11],"still":[12],"lags":[13],"behind":[14],"hybrid":[15],"CTC/attention":[16],"systems.":[17],"This":[18],"paper":[19],"introduces":[20],"Hypformer,":[21],"a":[22,91],"fast":[23,35],"hypothesis-driven":[24],"rescoring":[25,42,45,64],"speech":[26],"recognition":[27,110],"framework.":[28],"Multiple":[29],"hypothetical":[30],"prefixes":[31],"are":[32],"realized":[33],"by":[34,111],"prefix":[36],"generation":[37],"algorithm.":[38],"With":[39],"two":[40],"different":[41],"methods,":[43],"nar-ar":[44],"and":[46,58,75],"nar<inline-formula":[47],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[48],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[49],"notation=\"LaTeX\">$^{2}$</tex-math></inline-formula>":[50],"rescoring,":[51],"Hypformer":[52,79,106],"can":[53],"flexibly":[54],"switch":[55],"between":[56],"autoregressive":[57],"decoding":[60],"modes":[61],"to":[62],"perform":[63],"hypothesis":[66],"prefixes.":[67],"Experiments":[68,97],"on":[69,98],"standard":[71],"Mandarin":[72,100],"datasets":[73],"AISHELL-1":[74],"AISHELL-2":[76],"demonstrate":[77],"that":[78,105],"outperforms":[80],"state-of-the-art":[82],"Hybrid":[83],"CTC/Attention":[84],"systems":[85],"in":[86],"while":[89],"achieving":[90],"speedup":[92],"over":[94],"six":[95],"times.":[96],"sub-dialect":[101],"dataset":[102],"KeSpeech":[103],"indicate":[104],"achieves":[107],"more":[108],"accurate":[109],"leveraging":[112],"richer":[113],"contextual":[114],"information.":[115]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}