{"id":"https://openalex.org/W2932675979","doi":"https://doi.org/10.1109/icassp.2019.8682903","title":"Acoustically Grounded Word Embeddings for Improved Acoustics-to-word Speech Recognition","display_name":"Acoustically Grounded Word Embeddings for Improved Acoustics-to-word Speech Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2932675979","doi":"https://doi.org/10.1109/icassp.2019.8682903","mag":"2932675979"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682903","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":["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/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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TTI-Chicago","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015927589","display_name":"Kartik Audhkhasi","orcid":"https://orcid.org/0000-0002-2340-1144"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kartik Audhkhasi","raw_affiliation_strings":["IBM Research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TTI-Chicago","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Picheny","raw_affiliation_strings":["IBM Research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"269","issue":null,"first_page":"5641","last_page":"5645"},"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/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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.7991519570350647},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7720347046852112},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6975080966949463},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6849962472915649},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48073482513427734},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.4555988013744354},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44504427909851074},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4437014162540436},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.42767494916915894},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4121345281600952},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.1671755313873291},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.124542236328125},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07795077562332153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7991519570350647},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7720347046852112},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6975080966949463},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6849962472915649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48073482513427734},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.4555988013744354},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44504427909851074},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4437014162540436},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.42767494916915894},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4121345281600952},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.1671755313873291},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.124542236328125},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07795077562332153},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682903","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1496120315","https://openalex.org/W1522301498","https://openalex.org/W2059652594","https://openalex.org/W2091812280","https://openalex.org/W2096733369","https://openalex.org/W2147152072","https://openalex.org/W2153579005","https://openalex.org/W2190506272","https://openalex.org/W2250539671","https://openalex.org/W2291770225","https://openalex.org/W2296681920","https://openalex.org/W2513848549","https://openalex.org/W2545177271","https://openalex.org/W2566587499","https://openalex.org/W2578392894","https://openalex.org/W2597757402","https://openalex.org/W2884254529","https://openalex.org/W2884305338","https://openalex.org/W2884975363","https://openalex.org/W2899771611","https://openalex.org/W2936995161","https://openalex.org/W2951216052","https://openalex.org/W2962736743","https://openalex.org/W2962824709","https://openalex.org/W2962980711","https://openalex.org/W2963070863","https://openalex.org/W2963414781","https://openalex.org/W2963425185","https://openalex.org/W2963483399","https://openalex.org/W2963571336","https://openalex.org/W2963970535","https://openalex.org/W2964121744","https://openalex.org/W2998704965","https://openalex.org/W3099206234","https://openalex.org/W4285719527","https://openalex.org/W4294170691","https://openalex.org/W6631190155","https://openalex.org/W6680532216","https://openalex.org/W6682691769","https://openalex.org/W6697456849","https://openalex.org/W6731763572","https://openalex.org/W6752958021","https://openalex.org/W6753411874","https://openalex.org/W6756040250","https://openalex.org/W6761030284"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2161474341","https://openalex.org/W2037549926","https://openalex.org/W1997182898","https://openalex.org/W2401522294","https://openalex.org/W1962828410","https://openalex.org/W2253780618","https://openalex.org/W4205429340","https://openalex.org/W4232239836","https://openalex.org/W2079838398"],"abstract_inverted_index":{"Direct":[0],"acoustics-to-word":[1],"(A2W)":[2],"systems":[3,24],"for":[4,134],"end-to-end":[5],"automatic":[6],"speech":[7],"recognition":[8],"are":[9],"simpler":[10],"to":[11,16,98,156],"train,":[12],"and":[13,35,58,89,121,125,162],"more":[14],"efficient":[15],"decode":[17],"with,":[18],"than":[19],"sub-word":[20],"systems.":[21,66],"However,":[22],"A2W":[23,65,188],"can":[25,169],"have":[26],"difficulties":[27],"at":[28,36,114,131],"training":[29,44,115],"time":[30,38,116,133],"when":[31,39],"data":[32],"is":[33,69,142,146,148,164],"limited,":[34],"decoding":[37],"recognizing":[40],"words":[41],"outside":[42],"the":[43,52,73,100,118,122,128,158,184],"vocabulary.":[45],"To":[46],"address":[47],"these":[48],"shortcomings,":[49],"we":[50,107],"investigate":[51],"use":[53],"of":[54,78,85,95,102,176,186],"recently":[55],"proposed":[56],"acoustic":[57,152],"acoustically":[59,143],"grounded":[60],"word":[61,86,96,129,139],"embedding":[62,87,140],"techniques":[63,182],"in":[64],"The":[67],"idea":[68],"based":[70],"on":[71,190],"treating":[72],"final":[74],"pre-softmax":[75],"weight":[76],"matrix":[77,84],"an":[79,91,187],"AWE":[80],"recognizer":[81,123,189],"as":[82,155],"a":[83],"vectors,":[88],"using":[90,127],"externally":[92],"trained":[93],"set":[94],"embeddings":[97,120,130,153],"improve":[99,183],"quality":[101],"this":[103],"matrix.":[104],"In":[105],"particular":[106],"introduce":[108],"two":[109],"ideas:":[110],"(1)":[111],"Enforcing":[112],"similarity":[113],"between":[117],"external":[119],"weights,":[124],"(2)":[126],"test":[132],"predicting":[135],"out-of-vocabulary":[136],"words.":[137],"Our":[138],"model":[141],"grounded,":[144],"that":[145,167,180],"it":[147,163,168],"learned":[149],"jointly":[150],"with":[151],"so":[154,166],"encode":[157],"words'":[159],"acoustic-phonetic":[160],"content;":[161],"parametric,":[165],"embed":[170],"any":[171],"arbitrary":[172],"(potentially":[173],"out-of-vocabulary)":[174],"sequence":[175],"characters.":[177],"We":[178],"find":[179],"both":[181],"performance":[185],"conversational":[191],"telephone":[192],"speech.":[193]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}