{"id":"https://openalex.org/W4283700324","doi":"https://doi.org/10.21437/interspeech.2022-10340","title":"Pruned RNN-T for fast, memory-e\ufb00icient ASR training","display_name":"Pruned RNN-T for fast, memory-e\ufb00icient ASR training","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283700324","doi":"https://doi.org/10.21437/interspeech.2022-10340"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10340","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10340","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5040568268","display_name":"Fangjun Kuang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fangjun Kuang","raw_affiliation_strings":["Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liyong Guo","raw_affiliation_strings":["Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068307574","display_name":"Wei Kang","orcid":"https://orcid.org/0000-0003-0193-2654"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Kang","raw_affiliation_strings":["Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Long Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long Lin","raw_affiliation_strings":["Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingshuang Luo","raw_affiliation_strings":["Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zengwei Yao","raw_affiliation_strings":["Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"last","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 Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2068","last_page":"2072"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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/T12031","display_name":"Speech and dialogue systems","score":0.9912999868392944,"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":0.8845419883728027},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.867093563079834},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6135070323944092},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5377979278564453},{"id":"https://openalex.org/keywords/recursion","display_name":"Recursion (computer science)","score":0.518258810043335},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45064693689346313},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4351726174354553},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4182872772216797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3382878303527832},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28800535202026367},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.24818205833435059},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07932394742965698}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8845419883728027},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.867093563079834},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6135070323944092},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5377979278564453},{"id":"https://openalex.org/C168773036","wikidata":"https://www.wikidata.org/wiki/Q264164","display_name":"Recursion (computer science)","level":2,"score":0.518258810043335},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45064693689346313},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4351726174354553},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4182872772216797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3382878303527832},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28800535202026367},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.24818205833435059},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07932394742965698},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10340","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10340","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2407080277","https://openalex.org/W2936774411","https://openalex.org/W2962760690","https://openalex.org/W2962784628","https://openalex.org/W2963250244","https://openalex.org/W3007227084","https://openalex.org/W3015686596","https://openalex.org/W3097777922","https://openalex.org/W3146505093","https://openalex.org/W3167533889","https://openalex.org/W4290709727","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1976679120","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W4281614748","https://openalex.org/W2495256954","https://openalex.org/W2259317772"],"abstract_inverted_index":{"The":[0],"RNN-Transducer":[1],"(RNN-T)":[2],"framework":[3],"for":[4,13,68,70,77,89],"speech":[5],"recognition":[6],"has":[7],"been":[8],"growing":[9],"in":[10,60,101],"popularity,":[11],"particularly":[12],"deployed":[14],"real-time":[15],"ASR":[16],"systems,":[17],"because":[18],"it":[19,54],"combines":[20],"high":[21],"accuracy":[22],"with":[23],"naturally":[24],"streaming":[25],"recognition.One":[26],"of":[27,30,47],"the":[28,63,90,102,122],"drawbacks":[29],"RNN-T":[31,58,82,91],"is":[32,37,66,99,128],"that":[33,98],"its":[34],"loss":[35,59,83],"function":[36],"relatively":[38],"slow":[39],"to":[40,56,120],"compute,":[41],"and":[42,79,104,130],"can":[43,52,108],"use":[44,57,116],"a":[45,75,94],"lot":[46],"memory.Excessive":[48],"GPU":[49],"memory":[50],"usage":[51],"make":[53],"impractical":[55],"cases":[61],"where":[62],"vocabulary":[64],"size":[65],"large:":[67],"example,":[69],"Chinese":[71],"character-based":[72],"ASR.We":[73],"introduce":[74],"method":[76],"faster":[78],"more":[80],"memoryefficient":[81],"computation.We":[84],"first":[85],"obtain":[86],"pruning":[87,118],"bounds":[88,119],"recursion":[92],"using":[93,112],"simple":[95],"joiner":[96,125],"network":[97],"linear":[100],"encoder":[103],"decoder":[105],"embeddings;":[106],"we":[107],"evaluate":[109,121],"this":[110],"without":[111],"much":[113],"memory.We":[114],"then":[115],"those":[117],"full,":[123],"non-linear":[124],"network.The":[126],"code":[127],"open-sourced":[129],"publicly":[131],"available.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":10}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}