{"id":"https://openalex.org/W3095706145","doi":"https://doi.org/10.21437/interspeech.2020-2828","title":"Multilingual Jointly Trained Acoustic and Written Word Embeddings","display_name":"Multilingual Jointly Trained Acoustic and Written Word Embeddings","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095706145","doi":"https://doi.org/10.21437/interspeech.2020-2828","mag":"3095706145"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2828","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5069782842","display_name":"Yushi Hu","orcid":"https://orcid.org/0000-0002-7540-2413"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yushi Hu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007445208","display_name":"Shane Settle","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shane Settle","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karen Livescu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069782842"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4245,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.89756419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1052","last_page":"1056"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9901000261306763,"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":0.8577072620391846},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.730294942855835},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6844325661659241},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6390337347984314},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5986987948417664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.58970046043396},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5575827360153198},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5352799296379089},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5267038941383362},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5244507789611816},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.41616255044937134},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19162073731422424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8577072620391846},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.730294942855835},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6844325661659241},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6390337347984314},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5986987948417664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.58970046043396},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5575827360153198},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5352799296379089},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5267038941383362},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5244507789611816},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.41616255044937134},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19162073731422424},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2828","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2341338763","https://openalex.org/W2950183183","https://openalex.org/W2030799363","https://openalex.org/W2032415964","https://openalex.org/W2288425735","https://openalex.org/W2349923317","https://openalex.org/W2894081631","https://openalex.org/W2986063033","https://openalex.org/W2978114332","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Acoustic":[0],"word":[1,9,32,116],"embeddings":[2,17,25,33,36],"(AWEs)":[3],"are":[4],"vector":[5],"representations":[6],"of":[7,18,26,156],"spoken":[8,46],"segments.":[10],"AWEs":[11],"can":[12,80],"be":[13,82],"learned":[14],"jointly":[15,61],"with":[16],"character":[19,183],"sequences,":[20,184],"to":[21,40,56,103,106],"generate":[22],"phonetically":[23,71],"meaningful":[24],"written":[27],"words,":[28],"or":[29,88,152],"acoustically":[30],"grounded":[31],"(AGWEs).":[34],"Such":[35],"have":[37],"been":[38],"used":[39,83],"improve":[41],"speech":[42],"retrieval,":[43],"recognition,":[44],"and":[45,66,127,185],"term":[47],"discovery.":[48],"In":[49],"this":[50,54],"work,":[51],"we":[52],"extend":[53],"idea":[55],"multiple":[57,75],"low-resource":[58,93],"languages.":[59,76,94,121],"We":[60,95,111,174],"train":[62],"an":[63,67,101],"AWE":[64],"model":[65,135],"AGWE":[68],"model,":[69],"using":[70],"transcribed":[72],"data":[73,91,157],"from":[74,92,158],"The":[77],"pre-trained":[78,147],"models":[79,114,148],"then":[81],"for":[84,119],"unseen":[85,132,194],"zero-resource":[86],"languages,":[87],"fine-tuned":[89],"on":[90,115,124,129,149,169],"also":[96,175],"investigate":[97],"distinctive":[98,187],"features,":[99],"as":[100],"alternative":[102],"phone":[104],"labels,":[105],"better":[107,166],"share":[108],"cross-lingual":[109],"information.":[110],"test":[112],"our":[113,134],"discrimination":[117],"tasks":[118],"twelve":[120],"When":[122],"trained":[123],"eleven":[125],"languages":[126],"tested":[128],"the":[130,146,171,197],"remaining":[131],"language,":[133,161],"outperforms":[136],"traditional":[137],"unsupervised":[138],"approaches":[139],"like":[140],"dynamic":[141],"time":[142],"warping.":[143],"After":[144],"fine-tuning":[145],"one":[150],"hour":[151],"even":[153],"ten":[154],"minutes":[155],"a":[159],"new":[160],"performance":[162,181],"is":[163,190],"typically":[164],"much":[165],"than":[167],"training":[168],"only":[170],"target-language":[172],"data.":[173],"find":[176],"that":[177,186],"phonetic":[178],"supervision":[179,189],"improves":[180],"over":[182],"feature":[188],"helpful":[191],"in":[192,196],"handling":[193],"phones":[195],"target":[198],"language.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}