{"id":"https://openalex.org/W4375869165","doi":"https://doi.org/10.1109/icassp49357.2023.10094567","title":"Fast and Parallel Decoding for Transducer","display_name":"Fast and Parallel Decoding for Transducer","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869165","doi":"https://doi.org/10.1109/icassp49357.2023.10094567"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5037914140","display_name":"Wei Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Kang","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102707172","display_name":"Liyong Guo","orcid":"https://orcid.org/0009-0002-2465-3914"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyong Guo","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040568268","display_name":"Fangjun Kuang","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangjun Kuang","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075614707","display_name":"Long Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Lin","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010072640","display_name":"Mingshuang Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingshuang Luo","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066643565","display_name":"Zengwei Yao","orcid":"https://orcid.org/0000-0002-2331-2387"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengwei Yao","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100435428","display_name":"Xiaoyu Yang","orcid":"https://orcid.org/0000-0002-3570-8979"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Yang","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027217976","display_name":"Piotr \u017belasko","orcid":"https://orcid.org/0000-0002-8245-0413"},"institutions":[{"id":"https://openalex.org/I4210150811","display_name":"MeaningCloud (Spain)","ror":"https://ror.org/05s565w61","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210150811"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Piotr \u017belasko","raw_affiliation_strings":["Meaning.Team Inc,USA","Meaning.Team Inc, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meaning.Team Inc,USA","institution_ids":["https://openalex.org/I4210150811"]},{"raw_affiliation_string":"Meaning.Team Inc, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9990000128746033,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.8284603357315063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7587103843688965},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.7505248785018921},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7264196872711182},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.496526300907135},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.49034547805786133},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46764206886291504},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.4154203236103058},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.34293484687805176},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.28668051958084106},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09566327929496765}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.8284603357315063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7587103843688965},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.7505248785018921},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7264196872711182},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.496526300907135},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.49034547805786133},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46764206886291504},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.4154203236103058},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.34293484687805176},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28668051958084106},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09566327929496765},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2219249508","https://openalex.org/W2407080277","https://openalex.org/W2936774411","https://openalex.org/W2962760690","https://openalex.org/W2962780374","https://openalex.org/W2963250244","https://openalex.org/W2987019345","https://openalex.org/W3005302685","https://openalex.org/W3008174054","https://openalex.org/W3015194534","https://openalex.org/W3015686596","https://openalex.org/W3097777922","https://openalex.org/W3161375121","https://openalex.org/W4283700324","https://openalex.org/W4385245566","https://openalex.org/W6638749077","https://openalex.org/W6688816777","https://openalex.org/W6739901393","https://openalex.org/W6770245836","https://openalex.org/W6929543497"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2058965144"],"abstract_inverted_index":{"The":[0,132],"transducer":[1,29,65,100],"architecture":[2],"is":[3,15,30,33,154],"becoming":[4],"increasingly":[5],"popular":[6],"in":[7,22,37,99,108,150],"the":[8,26,73,78,88],"field":[9],"of":[10,25,28,48,64,90],"speech":[11],"recognition,":[12],"because":[13],"it":[14,32,103],"naturally":[16],"streaming":[17],"as":[18,20,145,147],"well":[19,146],"high":[21],"accuracy.":[23],"One":[24],"drawbacks":[27],"that":[31,50,92,124,136],"difficult":[34],"to":[35,44,67,106],"decode":[36,107],"a":[38,61],"fast":[39],"and":[40,82,156],"parallel":[41,109,120],"way":[42],"due":[43],"an":[45,115],"unconstrained":[46],"number":[47,89],"symbols":[49,91],"can":[51,93,125],"be":[52,94],"emitted":[53,95],"per":[54,96],"time":[55,97],"step.In":[56],"this":[57],"work,":[58],"we":[59,75,113,137],"introduce":[60],"constrained":[62],"version":[63],"loss":[66],"learn":[68],"strictly":[69],"monotonic":[70],"alignments":[71],"between":[72],"sequences;":[74],"also":[76],"improve":[77],"standard":[79],"greedy":[80],"search":[81,84,122],"beam":[83,121],"algorithms":[85],"by":[86],"limiting":[87],"step":[98],"decoding,":[101],"making":[102],"more":[104],"efficient":[105],"with":[110,127],"batches.":[111],"Furthermore,":[112],"propose":[114],"finite":[116],"state":[117],"automaton-based":[118],"(FSA)":[119],"algorithm":[123],"run":[126],"graphs":[128],"on":[129],"GPU":[130],"efficiently.":[131],"experiment":[133],"results":[134],"show":[135],"achieve":[138],"slight":[139],"word":[140],"error":[141],"rate":[142],"(WER)":[143],"improvement":[144],"significant":[148],"speedup":[149],"decoding.":[151],"Our":[152],"work":[153],"open-sourced":[155],"publicly":[157],"available":[158],"<sup":[159],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[160],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[161],".":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}