{"id":"https://openalex.org/W4372267461","doi":"https://doi.org/10.1109/icassp49357.2023.10096065","title":"Accelerating RNN-T Training and Inference Using CTC Guidance","display_name":"Accelerating RNN-T Training and Inference Using CTC Guidance","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267461","doi":"https://doi.org/10.1109/icassp49357.2023.10096065"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096065","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/A5100339989","display_name":"Yongqiang Wang","orcid":"https://orcid.org/0000-0002-8600-0276"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongqiang Wang","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"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/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhehuai Chen","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034878927","display_name":"Chengjian Zheng","orcid":"https://orcid.org/0000-0002-7867-3438"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chengjian Zheng","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433648","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-9505-1833"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107931312","display_name":"Wei Han","orcid":"https://orcid.org/0000-0003-0809-5465"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Han","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037705635","display_name":"Parisa Haghani","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Parisa Haghani","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8963512182235718},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.775351881980896},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7329718470573425},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.7048129439353943},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6026449799537659},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.560699462890625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48923802375793457},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46377912163734436},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.41974854469299316},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.34570667147636414},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33155161142349243}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8963512182235718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.775351881980896},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7329718470573425},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.7048129439353943},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6026449799537659},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.560699462890625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48923802375793457},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46377912163734436},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.41974854469299316},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34570667147636414},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33155161142349243},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096065","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":[{"id":"https://metadata.un.org/sdg/4","score":0.5899999737739563,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1533416326","https://openalex.org/W1828163288","https://openalex.org/W2109886035","https://openalex.org/W2121879602","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2143612262","https://openalex.org/W2157331557","https://openalex.org/W2327501763","https://openalex.org/W2515439472","https://openalex.org/W2545177271","https://openalex.org/W2548332580","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2963920996","https://openalex.org/W2972818416","https://openalex.org/W3007328579","https://openalex.org/W3042416212","https://openalex.org/W3096524176","https://openalex.org/W3097777922","https://openalex.org/W3105669983","https://openalex.org/W3139918052","https://openalex.org/W3149509723","https://openalex.org/W3160405885","https://openalex.org/W3198643121","https://openalex.org/W3208743843","https://openalex.org/W4283700324","https://openalex.org/W4294619417","https://openalex.org/W4384519051","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6679436768","https://openalex.org/W6746892368","https://openalex.org/W6747158283","https://openalex.org/W6791904447","https://openalex.org/W6839049670"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1732468982","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W350032239","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W1596913645"],"abstract_inverted_index":{"We":[0,29,79,109,144],"propose":[1],"a":[2,22,31,43,116],"novel":[3],"method":[4,135,149],"to":[5,59,126,152],"accelerate":[6,153],"training":[7,104],"and":[8,70,105,141],"inference":[9,106,156],"process":[10],"of":[11,93,118],"recurrent":[12],"neural":[13],"network":[14],"transducer":[15],"(RNN-T)":[16],"based":[17],"on":[18,138],"the":[19,47,63,76,91,94,103,113,119,139,147,154],"guidance":[20],"from":[21,75],"co-trained":[23],"connectionist":[24],"temporal":[25],"classification":[26],"(CTC)":[27],"model.":[28],"made":[30],"key":[32],"assumption":[33],"that":[34,53,82,112,146],"if":[35],"an":[36],"encoder":[37],"embedding":[38],"frame":[39,45,55,84],"is":[40,51,136,150],"classified":[41],"as":[42],"blank":[44,60],"by":[46,157],"CTC":[48,114,120],"model,":[49],"it":[50,71],"likely":[52],"this":[54,83],"will":[56],"be":[57,73,88,124],"aligned":[58],"for":[61,102,130],"all":[62],"partial":[64],"alignments":[65],"or":[66,162],"hypotheses":[67],"in":[68,90,98,107],"RNN-T":[69,131,155],"can":[72,87,122],"discarded":[74],"decoder":[77],"input.":[78],"also":[80,123],"show":[81,111],"reduction":[85,129],"operation":[86],"applied":[89],"middle":[92],"encoder,":[95],"which":[96],"result":[97],"significant":[99],"speed":[100],"up":[101],"RNN-T.":[108],"further":[110],"alignment,":[115],"by-product":[117],"decoder,":[121],"used":[125],"perform":[127],"lattice":[128],"during":[132],"training.":[133],"Our":[134],"evaluated":[137],"Librispeech":[140],"SpeechStew":[142],"tasks.":[143],"demonstrate":[145],"proposed":[148],"able":[151],"2.2":[158],"times":[159],"with":[160],"similar":[161],"slightly":[163],"better":[164],"word":[165],"error":[166],"rates":[167],"(WER).":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}