{"id":"https://openalex.org/W3016190221","doi":"https://doi.org/10.1109/icassp40776.2020.9053736","title":"Learning a Subword Inventory Jointly with End-to-End Automatic Speech Recognition","display_name":"Learning a Subword Inventory Jointly with End-to-End Automatic Speech Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016190221","doi":"https://doi.org/10.1109/icassp40776.2020.9053736","mag":"3016190221"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5047280966","display_name":"Jennifer Drexler","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jennifer Drexler","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047280966"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.9279,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.7989766,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6439","last_page":"6443"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/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/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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/computer-science","display_name":"Computer science","score":0.7650085091590881},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.7148403525352478},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6191998720169067},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5722382068634033},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5268420577049255},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5213952660560608},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4777483344078064},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.41126328706741333},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4072125554084778},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3212270736694336},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09178471565246582}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7650085091590881},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7148403525352478},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6191998720169067},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5722382068634033},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5268420577049255},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5213952660560608},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4777483344078064},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.41126328706741333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4072125554084778},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3212270736694336},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09178471565246582},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W2064675550","https://openalex.org/W2327501763","https://openalex.org/W2530486890","https://openalex.org/W2799800213","https://openalex.org/W2938348542","https://openalex.org/W2952288254","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963953073","https://openalex.org/W2963979492","https://openalex.org/W4214717370","https://openalex.org/W6604254268","https://openalex.org/W6728811460","https://openalex.org/W6734588641"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W2151749779","https://openalex.org/W3008587939","https://openalex.org/W3196421258","https://openalex.org/W4387301579","https://openalex.org/W2763956190","https://openalex.org/W4400488565","https://openalex.org/W2380059383"],"abstract_inverted_index":{"Recent":[0],"work":[1,21],"has":[2],"demonstrated":[3],"the":[4,24,32,43,54,69,92,120,128,138],"promise":[5],"of":[6,34,102,137],"using":[7,58],"subword":[8,35,59,103,139],"units":[9,36,60],"as":[10,77],"output":[11],"targets":[12],"for":[13,57],"sequence-to-sequence":[14],"automatic":[15],"speech":[16,44],"recognition":[17],"(ASR)":[18],"models.":[19],"Our":[20],"builds":[22],"on":[23,41,127],"latent":[25],"sequence":[26],"decomposition":[27,115],"(LSD)":[28],"framework,":[29],"in":[30,37],"which":[31,105],"use":[33],"ASR":[38,70],"is":[39,106,111],"dependent":[40],"both":[42],"input":[45],"and":[46],"text":[47],"output.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,133],"follow":[53],"LSD":[55,93],"method":[56],"but":[61],"introduce":[62],"an":[63,113,135],"updated":[64],"loss":[65,84,90],"function":[66,85],"that":[67,81,98],"allows":[68],"model":[71],"to":[72],"explicitly":[73],"perform":[74],"unit":[75],"discovery,":[76],"well.":[78],"We":[79,95],"show":[80,97],"our":[82,143],"n-gram":[83,121],"outperforms":[86],"standard":[87],"maximum":[88],"likelihood":[89],"within":[91],"framework.":[94],"also":[96,112],"uniform":[99],"greedy":[100],"sampling":[101],"units,":[104],"much":[107],"faster":[108],"than":[109],"LSD,":[110],"effective":[114],"strategy":[116],"when":[117],"combined":[118],"with":[119,124],"loss.":[122],"Along":[123],"quantitative":[125],"results":[126],"Wall":[129],"Street":[130],"Journal":[131],"Corpus,":[132],"present":[134],"analysis":[136],"inventory":[140],"learned":[141],"by":[142],"model.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}