{"id":"https://openalex.org/W3160729285","doi":"https://doi.org/10.1109/icassp39728.2021.9414509","title":"An Asynchronous WFST-Based Decoder for Automatic Speech Recognition","display_name":"An Asynchronous WFST-Based Decoder for Automatic Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160729285","doi":"https://doi.org/10.1109/icassp39728.2021.9414509","mag":"3160729285"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5100751610","display_name":"Hang Lv","orcid":"https://orcid.org/0000-0003-3761-1684"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Hang Lv","raw_affiliation_strings":["Audio, Speech and Language Processing Lab (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Center of Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","Audio, Speech and Language Processing Lab (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Lab (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Center of Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Lab (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002433660","display_name":"Zhehuai Chen","orcid":"https://orcid.org/0000-0003-4400-5340"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhehuai Chen","raw_affiliation_strings":["Center of Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034399968","display_name":"Hainan Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hainan Xu","raw_affiliation_strings":["Center of Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Xiaomi Corporation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Audio, Speech and Language Processing Lab (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Audio, Speech and Language Processing Lab (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Lab (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Lab (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Center of Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6019","last_page":"6023"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9969000220298767,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9965999722480774,"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/decoding-methods","display_name":"Decoding methods","score":0.8397941589355469},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7888956069946289},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6844273805618286},{"id":"https://openalex.org/keywords/soft-decision-decoder","display_name":"Soft-decision decoder","score":0.6376438140869141},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5827018618583679},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5224708318710327},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5193592309951782},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.4503057897090912},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.443642795085907},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3661465346813202},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.336750328540802}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.8397941589355469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7888956069946289},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6844273805618286},{"id":"https://openalex.org/C185588885","wikidata":"https://www.wikidata.org/wiki/Q7553811","display_name":"Soft-decision decoder","level":3,"score":0.6376438140869141},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5827018618583679},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5224708318710327},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5193592309951782},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.4503057897090912},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.443642795085907},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3661465346813202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.336750328540802},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W27187656","https://openalex.org/W181370797","https://openalex.org/W1494198834","https://openalex.org/W1508752711","https://openalex.org/W1515156256","https://openalex.org/W1524333225","https://openalex.org/W1528470941","https://openalex.org/W2046932483","https://openalex.org/W2083503896","https://openalex.org/W2116047093","https://openalex.org/W2132991150","https://openalex.org/W2149910709","https://openalex.org/W2164579587","https://openalex.org/W2293829681","https://openalex.org/W2395294869","https://openalex.org/W2402146185","https://openalex.org/W2514741789","https://openalex.org/W2515439472","https://openalex.org/W2729190387","https://openalex.org/W2749241159","https://openalex.org/W2802201485","https://openalex.org/W3149242827","https://openalex.org/W6630493794","https://openalex.org/W6631362777","https://openalex.org/W6712409652","https://openalex.org/W6712930963"],"related_works":["https://openalex.org/W2154078079","https://openalex.org/W4244085088","https://openalex.org/W406587413","https://openalex.org/W2141913236","https://openalex.org/W2889372359","https://openalex.org/W2148484519","https://openalex.org/W2590897469","https://openalex.org/W2391909979","https://openalex.org/W1967516765","https://openalex.org/W1646009337"],"abstract_inverted_index":{"We":[0],"introduce":[1],"asynchronous":[2,42],"dynamic":[3,43],"decoder,":[4,105],"which":[5,34],"adopts":[6],"an":[7,84],"efficient":[8],"A*":[9],"algorithm":[10],"to":[11],"incorporate":[12],"big":[13],"language":[14],"models":[15],"in":[16,69,74],"the":[17,41,59,65,70,79,91,98,107,114],"one-pass":[18,28,81,100],"decoding":[19,29,71,82,101],"for":[20],"large":[21],"vocabulary":[22],"continuous":[23],"speech":[24],"recognition.":[25],"Unlike":[26],"standard":[27,80,99],"with":[30,54,83,102,113],"on-the-fly":[31,85,103],"composition":[32,86,104],"decoder":[33,44,93],"might":[35],"induce":[36],"a":[37,46],"significant":[38],"computation":[39,63],"overhead,":[40],"has":[45,51],"novel":[47],"design":[48],"where":[49],"it":[50],"two":[52,66],"fronts,":[53],"one":[55],"performing":[56],"\"exploration\"":[57],"and":[58],"other":[60],"\"backfill\".":[61],"The":[62],"of":[64,116],"fronts":[67],"alternates":[68],"process,":[72],"resulting":[73],"more":[75,111],"effective":[76],"pruning":[77],"than":[78,97],"decoder.":[87],"Experiments":[88],"show":[89],"that":[90],"proposed":[92],"works":[94],"notably":[95],"faster":[96],"while":[106],"acceleration":[108],"will":[109],"be":[110],"obvious":[112],"increment":[115],"data":[117],"complexity.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
