{"id":"https://openalex.org/W4225824617","doi":"https://doi.org/10.21437/interspeech.2022-787","title":"Memory-Efficient Training of RNN-Transducer with Sampled Softmax","display_name":"Memory-Efficient Training of RNN-Transducer with Sampled Softmax","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4225824617","doi":"https://doi.org/10.21437/interspeech.2022-787"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-787","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-787","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/A5015578080","display_name":"Jaesong Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaesong Lee","raw_affiliation_strings":["Naver Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Naver Corporation","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065076995","display_name":"Lukas Jyuhn\u2010Hsiarn Lee","orcid":"https://orcid.org/0000-0003-1095-6877"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Lukas Lee","raw_affiliation_strings":["Naver Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Naver Corporation","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8435,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7343433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4441","last_page":"4445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.996999979019165,"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":0.996999979019165,"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/T10320","display_name":"Neural Networks and Applications","score":0.992900013923645,"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/T10346","display_name":"Magnetic confinement fusion research","score":0.9689000248908997,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.9065103530883789},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6727460622787476},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6116223335266113},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.551406979560852},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5214442610740662},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3677985668182373},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35494932532310486},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1849474310874939},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16619077324867249},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1386968493461609},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08183181285858154}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.9065103530883789},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6727460622787476},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6116223335266113},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.551406979560852},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5214442610740662},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3677985668182373},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35494932532310486},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1849474310874939},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16619077324867249},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1386968493461609},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08183181285858154},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-787","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-787","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":0.6299999952316284,"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/W37526647","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W1922655562","https://openalex.org/W2100664567","https://openalex.org/W2143612262","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2936774411","https://openalex.org/W2962760690","https://openalex.org/W2962780374","https://openalex.org/W2962824709","https://openalex.org/W2963211739","https://openalex.org/W2963242190","https://openalex.org/W2963250244","https://openalex.org/W2963414781","https://openalex.org/W2963827914","https://openalex.org/W3007227084","https://openalex.org/W3008898571","https://openalex.org/W3011207290","https://openalex.org/W3015315932","https://openalex.org/W3015960524","https://openalex.org/W3036601975","https://openalex.org/W3094979069","https://openalex.org/W3097777922","https://openalex.org/W3160987270","https://openalex.org/W3162249256","https://openalex.org/W3162649911","https://openalex.org/W3163300396","https://openalex.org/W3197140813","https://openalex.org/W3197813307","https://openalex.org/W4210663600","https://openalex.org/W4226052192","https://openalex.org/W4287605195","https://openalex.org/W4287989347","https://openalex.org/W4294619417"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3108503355","https://openalex.org/W4226420367","https://openalex.org/W2962876041","https://openalex.org/W3090555870","https://openalex.org/W3022820045","https://openalex.org/W2801655600","https://openalex.org/W3005627584","https://openalex.org/W4303493643"],"abstract_inverted_index":{"RNN-Transducer":[0,12],"has":[1,13,29],"been":[2,30],"one":[3],"of":[4,52,75,106],"promising":[5],"architectures":[6],"for":[7,34,69,79],"end-to-end":[8],"automatic":[9],"speech":[10],"recognition.Although":[11],"many":[14],"advantages":[15],"including":[16],"its":[17,23,58],"strong":[18],"accuracy":[19,105],"and":[20,72,92,101],"streaming-friendly":[21],"property,":[22],"high":[24],"memory":[25,59,67,99],"consumption":[26,68,100],"during":[27,54],"training":[28,55],"a":[31,49,70],"critical":[32],"problem":[33],"development.In":[35],"this":[36],"work,":[37],"we":[38],"propose":[39],"to":[40,44,65,82],"apply":[41],"sampled":[42,63,95],"softmax":[43,64,96],"RNN-Transducer,":[45],"which":[46],"requires":[47],"only":[48],"small":[50],"subset":[51],"vocabulary":[53,81],"thus":[56],"saves":[57],"consumption.We":[60],"further":[61],"extend":[62],"optimize":[66],"minibatch,":[71],"employ":[73],"distributions":[74],"auxiliary":[76],"CTC":[77],"losses":[78],"sampling":[80],"improve":[83],"model":[84],"accuracy.We":[85],"present":[86],"experimental":[87],"results":[88],"on":[89],"LibriSpeech,":[90],"AISHELL-1,":[91],"CSJ-APS,":[93],"where":[94],"greatly":[97],"reduces":[98],"still":[102],"maintains":[103],"the":[104,107],"baseline":[108],"model.":[109]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}