{"id":"https://openalex.org/W7148604914","doi":"https://doi.org/10.1109/asru65441.2025.11434636","title":"FlexCTC: GPU-powered CTC Beam Decoding With Advanced Contextual Abilities","display_name":"FlexCTC: GPU-powered CTC Beam Decoding With Advanced Contextual Abilities","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148604914","doi":"https://doi.org/10.1109/asru65441.2025.11434636"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132791755","display_name":"Lilit Grigoryan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lilit Grigoryan","raw_affiliation_strings":["NVIDIA,Yerevan,Armenia"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Yerevan,Armenia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132811057","display_name":"Vladimir Bataev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vladimir Bataev","raw_affiliation_strings":["NVIDIA,Yerevan,Armenia"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Yerevan,Armenia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132814380","display_name":"Nikolay Karpov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolay Karpov","raw_affiliation_strings":["NVIDIA,Yerevan,Armenia"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Yerevan,Armenia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054253945","display_name":"Andrei Andrusenko","orcid":"https://orcid.org/0000-0002-8697-832X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrei Andrusenko","raw_affiliation_strings":["NVIDIA,Yerevan,Armenia"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Yerevan,Armenia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026088310","display_name":"Vitaly Lavrukhin","orcid":"https://orcid.org/0009-0006-7866-8301"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vitaly Lavrukhin","raw_affiliation_strings":["NVIDIA,Santa Clara,USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":["NVIDIA,Santa Clara,USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5132791755"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4014,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93506107,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9083999991416931,"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":0.9083999991416931,"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":0.03009999915957451,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.021900000050663948,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5322999954223633},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5285999774932861},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.499099999666214},{"id":"https://openalex.org/keywords/beam-search","display_name":"Beam search","score":0.4318000078201294},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4309000074863434},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.42489999532699585},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.374099999666214},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.32580000162124634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8112999796867371},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5322999954223633},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5285999774932861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5011000037193298},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.499099999666214},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.4318000078201294},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.42489999532699585},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4163999855518341},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.39089998602867126},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35109999775886536},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3476000130176544},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.32580000162124634},{"id":"https://openalex.org/C2780615140","wikidata":"https://www.wikidata.org/wiki/Q920419","display_name":"Upgrade","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3156000077724457},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.31130000948905945},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.27300000190734863},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C41661131","wikidata":"https://www.wikidata.org/wiki/Q220764","display_name":"Interrupt","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4000052511692047,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2963362078","https://openalex.org/W2972780808","https://openalex.org/W3085139254","https://openalex.org/W3097777922","https://openalex.org/W3197674197","https://openalex.org/W3198587774","https://openalex.org/W4297727296","https://openalex.org/W4391021768","https://openalex.org/W4412886866","https://openalex.org/W4415433345","https://openalex.org/W4415433485","https://openalex.org/W7148430238"],"related_works":[],"abstract_inverted_index":{"While":[0],"beam":[1,34],"search":[2],"improves":[3],"speech":[4],"recognition":[5],"quality":[6],"over":[7],"greedy":[8],"decoding,":[9,35,106],"standard":[10],"implementations":[11],"are":[12],"slow,":[13],"often":[14],"sequential,":[15],"and":[16,47,54,77,97,104,113],"CPU-bound.":[17],"To":[18],"fully":[19,32,69],"leverage":[20],"modern":[21],"hardware":[22],"capabilities,":[23],"we":[24],"present":[25],"a":[26,51,67],"novel":[27],"open-source":[28],"FlexCTC":[29],"toolkit":[30,65],"for":[31,37,110],"GPU-based":[33],"designed":[36],"Connectionist":[38],"Temporal":[39],"Classification":[40],"(CTC)":[41],"models.":[42],"Developed":[43],"entirely":[44],"in":[45],"Python":[46],"PyTorch,":[48],"it":[49],"offers":[50],"fast,":[52],"user-friendly,":[53],"extensible":[55],"alternative":[56],"to":[57],"traditional":[58],"C++,":[59],"CUDA,":[60],"or":[61],"WFST-based":[62],"decoders.":[63],"The":[64],"features":[66,101],"high-performance,":[68],"batched":[70],"GPU":[71],"implementation":[72],"with":[73],"eliminated":[74],"CPU-GPU":[75],"synchronization":[76],"minimized":[78],"kernel":[79],"launch":[80],"overhead":[81],"via":[82],"CUDA":[83],"Graphs.":[84],"It":[85],"also":[86],"supports":[87],"advanced":[88],"contextualization":[89],"techniques,":[90],"including":[91],"GPU-powered":[92],"N-gram":[93],"language":[94],"model":[95],"fusion":[96],"phrase-level":[98],"boosting.":[99],"These":[100],"enable":[102],"accurate":[103],"efficient":[105],"making":[107],"them":[108],"suitable":[109],"both":[111],"research":[112],"production":[114],"use.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}