{"id":"https://openalex.org/W2916685081","doi":"https://doi.org/10.1109/icassp.2019.8683868","title":"Learned in Speech Recognition: Contextual Acoustic Word Embeddings","display_name":"Learned in Speech Recognition: Contextual Acoustic Word Embeddings","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2916685081","doi":"https://doi.org/10.1109/icassp.2019.8683868","mag":"2916685081"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1902.06833","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036933477","display_name":"Shruti Palaskar","orcid":"https://orcid.org/0000-0001-8637-1897"},"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":"Shruti Palaskar","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, U.S.A","Carnegie Mellon University,Pittsburgh,PA,U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035694997","display_name":"Vikas Raunak","orcid":null},"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":"Vikas Raunak","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, U.S.A","Carnegie Mellon University,Pittsburgh,PA,U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"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":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, U.S.A","Carnegie Mellon University,Pittsburgh,PA,U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,U.S.A","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.1093,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.34632878,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"6530","last_page":"6534"},"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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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":0.9986000061035156,"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/computer-science","display_name":"Computer science","score":0.8402695655822754},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6682012677192688},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.639204204082489},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6103053689002991},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5521197319030762},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5384433269500732},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.48317351937294006},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48143714666366577},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.46897658705711365},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4628177881240845},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44422900676727295},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4221761226654053},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.41907206177711487},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.29225730895996094},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13553616404533386},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.10102257132530212}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8402695655822754},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6682012677192688},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.639204204082489},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6103053689002991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5521197319030762},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5384433269500732},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.48317351937294006},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48143714666366577},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.46897658705711365},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4628177881240845},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44422900676727295},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4221761226654053},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.41907206177711487},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29225730895996094},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13553616404533386},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.10102257132530212},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2019.8683868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1902.06833","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.06833","pdf_url":"https://arxiv.org/pdf/1902.06833","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2916685081","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1902.06833","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1902.06833","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1902.06833","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1902.06833","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.06833","pdf_url":"https://arxiv.org/pdf/1902.06833","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310207","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33"},{"id":"https://openalex.org/F4320337968","display_name":"Center for Machine Learning and Health, School of Computer Science, Carnegie Mellon University","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2916685081.pdf","grobid_xml":"https://content.openalex.org/works/W2916685081.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2091671846","https://openalex.org/W2127141656","https://openalex.org/W2137010615","https://openalex.org/W2166637769","https://openalex.org/W2190506272","https://openalex.org/W2250539671","https://openalex.org/W2327501763","https://openalex.org/W2399456070","https://openalex.org/W2608712415","https://openalex.org/W2773095876","https://openalex.org/W2775304348","https://openalex.org/W2787560479","https://openalex.org/W2790235966","https://openalex.org/W2791164268","https://openalex.org/W2794753807","https://openalex.org/W2799800213","https://openalex.org/W2807071886","https://openalex.org/W2884483159","https://openalex.org/W2899274165","https://openalex.org/W2949888546","https://openalex.org/W2951216052","https://openalex.org/W2951327905","https://openalex.org/W2952021518","https://openalex.org/W2962739339","https://openalex.org/W2962862718","https://openalex.org/W2962961016","https://openalex.org/W2963414781","https://openalex.org/W2963425185","https://openalex.org/W2963879199","https://openalex.org/W2963970535","https://openalex.org/W6623517193","https://openalex.org/W6637373629","https://openalex.org/W6679436768","https://openalex.org/W6682691769","https://openalex.org/W6697456849","https://openalex.org/W6728910023","https://openalex.org/W6731763572","https://openalex.org/W6742080785","https://openalex.org/W6746497681","https://openalex.org/W6746892368","https://openalex.org/W6748452836","https://openalex.org/W6755559483"],"related_works":["https://openalex.org/W2953090514","https://openalex.org/W2963658982","https://openalex.org/W2408289839","https://openalex.org/W3095706145","https://openalex.org/W3102259066","https://openalex.org/W3015325583","https://openalex.org/W2262099980","https://openalex.org/W2293858598","https://openalex.org/W2951327905","https://openalex.org/W2075815989","https://openalex.org/W2033350476","https://openalex.org/W3011209123","https://openalex.org/W2773095876","https://openalex.org/W1603190341","https://openalex.org/W3131709275","https://openalex.org/W3034461631","https://openalex.org/W3027851323","https://openalex.org/W2796182971","https://openalex.org/W2804648901","https://openalex.org/W1498597639"],"abstract_inverted_index":{"End-to-end":[0],"acoustic-to-word":[1,81],"speech":[2,82,111,142],"recognition":[3,83,143],"models":[4,32],"have":[5],"recently":[6],"gained":[7],"popularity":[8],"because":[9,47],"they":[10],"are":[11],"easy":[12],"to":[13,17,37,54,70],"train,":[14],"scale":[15],"well":[16],"large":[18],"amounts":[19],"of":[20,61,93,133,139],"training":[21],"data,":[22],"and":[23,125,144],"do":[24],"not":[25],"require":[26],"a":[27,78,91,105,120,137],"lexicon.":[28],"In":[29,64,113],"addition,":[30,114],"word":[31,74,147],"may":[33],"also":[34],"be":[35],"easier":[36],"integrate":[38],"with":[39],"downstream":[40],"tasks":[41],"such":[42],"as":[43],"spoken":[44,121],"language":[45,122],"understanding,":[46],"inference":[48],"(search)":[49],"is":[50],"much":[51],"simplified":[52],"compared":[53],"phoneme,":[55],"character":[56],"or":[57],"any":[58],"other":[59],"sort":[60],"sub-word":[62],"units.":[63],"this":[65],"paper,":[66],"we":[67,115],"describe":[68],"methods":[69],"construct":[71],"contextual":[72],"acoustic":[73],"embeddings":[75,100,118,129,135,148],"directly":[76],"from":[77,149],"supervised":[79],"sequence-to-sequence":[80],"model":[84,107],"using":[85],"the":[86,110,131],"learned":[87],"attention":[88],"distribution.":[89],"On":[90],"suite":[92],"16":[94],"standard":[95],"sentence":[96],"evaluation":[97],"tasks,":[98],"our":[99,128],"show":[101],"competitive":[102],"performance":[103,132],"against":[104],"word2vec":[106],"trained":[108],"on":[109,119],"transcriptions.":[112,150],"evaluate":[116],"these":[117],"understanding":[123],"task,":[124],"observe":[126],"that":[127],"match":[130],"text-based":[134],"in":[136],"pipeline":[138],"first":[140],"performing":[141],"then":[145],"constructing":[146]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}