{"id":"https://openalex.org/W3150750326","doi":"https://doi.org/10.1109/slt48900.2021.9383578","title":"Whole-Word Segmental Speech Recognition with Acoustic Word Embeddings","display_name":"Whole-Word Segmental Speech Recognition with Acoustic Word Embeddings","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3150750326","doi":"https://doi.org/10.1109/slt48900.2021.9383578","mag":"3150750326"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5085193896","display_name":"Bowen Shi","orcid":"https://orcid.org/0000-0002-4753-7572"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bowen Shi","raw_affiliation_strings":["TTI, Chicago, USA"],"affiliations":[{"raw_affiliation_string":"TTI, Chicago, USA","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007445208","display_name":"Shane Settle","orcid":null},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shane Settle","raw_affiliation_strings":["TTI, Chicago, USA"],"affiliations":[{"raw_affiliation_string":"TTI, Chicago, USA","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karen Livescu","raw_affiliation_strings":["TTI, Chicago, USA"],"affiliations":[{"raw_affiliation_string":"TTI, Chicago, USA","institution_ids":["https://openalex.org/I160992636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085193896"],"corresponding_institution_ids":["https://openalex.org/I160992636"],"apc_list":null,"apc_paid":null,"fwci":0.56,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.72305466,"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":"164","last_page":"171"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/word","display_name":"Word (group theory)","score":0.8064149618148804},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7966088056564331},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7637567520141602},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6568785905838013},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.6365331411361694},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.5612697601318359},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5269012451171875},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4982895851135254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4934307634830475},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4748040735721588},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44342437386512756},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4377742111682892},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.41806986927986145},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3799019455909729},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3617931604385376},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.3482125401496887},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14957407116889954},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1475335955619812},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09107965230941772},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07634943723678589}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.8064149618148804},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7966088056564331},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7637567520141602},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6568785905838013},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.6365331411361694},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.5612697601318359},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5269012451171875},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4982895851135254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4934307634830475},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4748040735721588},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44342437386512756},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4377742111682892},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.41806986927986145},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3799019455909729},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3617931604385376},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3482125401496887},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14957407116889954},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1475335955619812},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09107965230941772},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07634943723678589},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.699999988079071,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1039360507","display_name":null,"funder_award_id":"IIS-1816627","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5797461078","display_name":"RI: Small: From acoustics to semantics:  Embedding speech for a hierarchy of tasks","funder_award_id":"1816627","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1614298861","https://openalex.org/W2083393647","https://openalex.org/W2096733369","https://openalex.org/W2111535841","https://openalex.org/W2111732304","https://openalex.org/W2127141656","https://openalex.org/W2131033001","https://openalex.org/W2151660570","https://openalex.org/W2166637769","https://openalex.org/W2190506272","https://openalex.org/W2196580907","https://openalex.org/W2250539671","https://openalex.org/W2287914047","https://openalex.org/W2296681920","https://openalex.org/W2395342389","https://openalex.org/W2403307209","https://openalex.org/W2403708103","https://openalex.org/W2545177271","https://openalex.org/W2566587499","https://openalex.org/W2578392894","https://openalex.org/W2597757402","https://openalex.org/W2741480356","https://openalex.org/W2884483159","https://openalex.org/W2888884590","https://openalex.org/W2896457183","https://openalex.org/W2899879954","https://openalex.org/W2932675979","https://openalex.org/W2936774411","https://openalex.org/W2951216052","https://openalex.org/W2952886436","https://openalex.org/W2962736743","https://openalex.org/W2962739339","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2962875366","https://openalex.org/W2962980711","https://openalex.org/W2963070863","https://openalex.org/W2963341956","https://openalex.org/W2963688273","https://openalex.org/W2963795358","https://openalex.org/W2963970535","https://openalex.org/W2964121744","https://openalex.org/W2970971581","https://openalex.org/W2973138437","https://openalex.org/W3099206234","https://openalex.org/W4295312788","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6636510571","https://openalex.org/W6696116229","https://openalex.org/W6697456849","https://openalex.org/W6713457929","https://openalex.org/W6728910023","https://openalex.org/W6731763572","https://openalex.org/W6755207826","https://openalex.org/W6764376188","https://openalex.org/W6766978945"],"related_works":["https://openalex.org/W2102309991","https://openalex.org/W1795315578","https://openalex.org/W2373954783","https://openalex.org/W2133857928","https://openalex.org/W2535886977","https://openalex.org/W2143297499","https://openalex.org/W2356694334","https://openalex.org/W2991144886","https://openalex.org/W2790444905","https://openalex.org/W1843778016"],"abstract_inverted_index":{"Segmental":[0],"models":[1,5,22,39,160],"are":[2,11,40],"sequence":[3],"prediction":[4,154],"in":[6],"which":[7,54],"scores":[8],"of":[9,17,36,46,58,103,118],"hypotheses":[10],"based":[12],"on":[13,84],"entire":[14],"variable-length":[15],"segments":[16],"frames.":[18],"We":[19,68,122],"consider":[20],"segmental":[21,76],"for":[23,73],"whole-word":[24,75],"(\"acoustic-to-word\")":[25],"speech":[26],"recognition,":[27],"with":[28,78,141,156],"the":[29,44,51,101,137,152],"feature":[30],"vectors":[31],"defined":[32],"using":[33,63],"vector":[34],"embeddings":[35,110,116],"segments.":[37],"Such":[38],"computationally":[41],"challenging":[42],"as":[43],"number":[45],"paths":[47],"is":[48],"proportional":[49],"to":[50],"vocabulary":[52],"size,":[53],"can":[55,128,147],"be":[56,129,148],"orders":[57],"magnitude":[59],"larger":[60],"than":[61],"when":[62],"subword":[64],"units":[65],"like":[66],"phones.":[67],"describe":[69],"an":[70],"efficient":[71],"approach":[72],"end-to-end":[74],"models,":[77],"forward-backward":[79],"and":[80,87,112,143],"Viterbi":[81],"decoding":[82],"performed":[83],"a":[85,88,132],"GPU":[86],"simple":[89],"segment":[90,139],"scoring":[91],"function":[92],"that":[93,124],"reduces":[94],"space":[95],"complexity.":[96],"In":[97],"addition,":[98],"we":[99],"investigate":[100],"use":[102],"pre-training":[104,136,151],"via":[105],"jointly":[106],"trained":[107],"acoustic":[108,138],"word":[109,115,120,125,153],"(AWEs)":[111],"acoustically":[113],"grounded":[114],"(AGWEs)":[117],"written":[119],"labels.":[121],"find":[123],"error":[126],"rate":[127],"reduced":[130],"by":[131,135,150],"large":[133],"margin":[134],"representation":[140],"AWEs,":[142],"additional":[144],"(smaller)":[145],"gains":[146],"obtained":[149],"layer":[155],"AGWEs.":[157],"Our":[158],"final":[159],"improve":[161],"over":[162],"prior":[163],"A2W":[164],"models.":[165]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}