{"id":"https://openalex.org/W3033831118","doi":"https://doi.org/10.1109/taslp.2021.3060805","title":"Improved Acoustic Word Embeddings for Zero-Resource Languages Using Multilingual Transfer","display_name":"Improved Acoustic Word Embeddings for Zero-Resource Languages Using Multilingual Transfer","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3033831118","doi":"https://doi.org/10.1109/taslp.2021.3060805","mag":"3033831118"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3060805","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3060805","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.02295","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040305929","display_name":"Herman Kamper","orcid":"https://orcid.org/0000-0003-2980-3475"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Herman Kamper","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, Stellenbosch University, Stellenbosch, South Africa","StellenBosch University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, Stellenbosch University, Stellenbosch, South Africa","institution_ids":["https://openalex.org/I26092322"]},{"raw_affiliation_string":"StellenBosch University","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078855278","display_name":"Yevgen Matusevych","orcid":"https://orcid.org/0000-0003-2910-4025"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yevgen Matusevych","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, U.K","University of Edinburgh,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"University of Edinburgh,","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075564798","display_name":"Sharon Goldwater","orcid":"https://orcid.org/0000-0002-7298-0947"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sharon Goldwater","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, U.K","University of Edinburgh,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"University of Edinburgh,","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.26,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62120142,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":"29","issue":null,"first_page":"1107","last_page":"1118"},"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/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/T10028","display_name":"Topic Modeling","score":0.9966999888420105,"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":0.7961223125457764},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6231186389923096},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5940302014350891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5669888257980347},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5459812879562378},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49332061409950256},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.47573113441467285},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4459637701511383},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4297362267971039},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.27504682540893555},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1265857219696045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7961223125457764},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6231186389923096},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5940302014350891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5669888257980347},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5459812879562378},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49332061409950256},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.47573113441467285},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4459637701511383},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4297362267971039},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27504682540893555},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1265857219696045},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/taslp.2021.3060805","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3060805","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2006.02295","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.02295","pdf_url":"https://arxiv.org/pdf/2006.02295","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/f75e5119-9bff-47c4-9551-c0a185756133","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/f75e5119-9bff-47c4-9551-c0a185756133","pdf_url":"https://www.research.ed.ac.uk/files/196162334/Improved_acoustic_word_KAMPER_DOA15022021_AFV.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kamper, H, Matusevych, Y & Goldwater, S 2021, 'Improved acoustic word embeddings for zero-resource languages using multilingual transfer', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 29, pp. 1107 - 1118. https://doi.org/10.1109/TASLP.2021.3060805","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.ed.ac.uk:publications/f75e5119-9bff-47c4-9551-c0a185756133","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f75e5119-9bff-47c4-9551-c0a185756133","pdf_url":"http://hdl.handle.net/20.500.11820/f75e5119-9bff-47c4-9551-c0a185756133","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kamper, H, Matusevych, Y & Goldwater, S 2021, 'Improved acoustic word embeddings for zero-resource languages using multilingual transfer', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 29, pp. 1107 - 1118. https://doi.org/10.1109/TASLP.2021.3060805","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"mag:3033831118","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2006.02295.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2006.02295","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.02295","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:2006.02295","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.02295","pdf_url":"https://arxiv.org/pdf/2006.02295","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1108956462","display_name":"Modeling the Development of Phonetic Representations","funder_award_id":"ES/R006660/1","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"},{"id":"https://openalex.org/G3923731482","display_name":null,"funder_award_id":"ES/R006660/1","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"},{"id":"https://openalex.org/G8880628323","display_name":null,"funder_award_id":"120409","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320306183","display_name":"James S. McDonnell Foundation","ror":"https://ror.org/03dy4aq19"},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320334630","display_name":"Economic and Social Research Council","ror":"https://ror.org/03n0ht308"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W1532499126","https://openalex.org/W1577418252","https://openalex.org/W1778492285","https://openalex.org/W1924770834","https://openalex.org/W1968147312","https://openalex.org/W1970890968","https://openalex.org/W1993660824","https://openalex.org/W2025482506","https://openalex.org/W2033436836","https://openalex.org/W2057007397","https://openalex.org/W2059652594","https://openalex.org/W2072054026","https://openalex.org/W2084534958","https://openalex.org/W2096733369","https://openalex.org/W2106053110","https://openalex.org/W2114347655","https://openalex.org/W2126203737","https://openalex.org/W2127589108","https://openalex.org/W2127982613","https://openalex.org/W2165698076","https://openalex.org/W2171019095","https://openalex.org/W2171590421","https://openalex.org/W2190506272","https://openalex.org/W2291770225","https://openalex.org/W2296681920","https://openalex.org/W2346964103","https://openalex.org/W2398490608","https://openalex.org/W2407151108","https://openalex.org/W2513848549","https://openalex.org/W2550241133","https://openalex.org/W2566587499","https://openalex.org/W2578392894","https://openalex.org/W2614542633","https://openalex.org/W2758697525","https://openalex.org/W2769437540","https://openalex.org/W2780786457","https://openalex.org/W2802557066","https://openalex.org/W2884305338","https://openalex.org/W2889313720","https://openalex.org/W2891816510","https://openalex.org/W2894835365","https://openalex.org/W2899518769","https://openalex.org/W2916113431","https://openalex.org/W2927191280","https://openalex.org/W2932675979","https://openalex.org/W2938991416","https://openalex.org/W2962736743","https://openalex.org/W2962850179","https://openalex.org/W2962980711","https://openalex.org/W2963259843","https://openalex.org/W2963425185","https://openalex.org/W2963431393","https://openalex.org/W2963620343","https://openalex.org/W2963720603","https://openalex.org/W2963879199","https://openalex.org/W2964121744","https://openalex.org/W2964169922","https://openalex.org/W2964309797","https://openalex.org/W2972764223","https://openalex.org/W2979736514","https://openalex.org/W2980988419","https://openalex.org/W3006358483","https://openalex.org/W3008444411","https://openalex.org/W3015325583","https://openalex.org/W3016368932","https://openalex.org/W3095706145","https://openalex.org/W3099206234","https://openalex.org/W3105242324","https://openalex.org/W6631190155","https://openalex.org/W6631637103","https://openalex.org/W6638159135","https://openalex.org/W6640212811","https://openalex.org/W6675751002","https://openalex.org/W6697357074","https://openalex.org/W6697456849","https://openalex.org/W6714100551","https://openalex.org/W6731763572","https://openalex.org/W6756497944","https://openalex.org/W6768896439","https://openalex.org/W6769247734","https://openalex.org/W6775659032","https://openalex.org/W6777330019"],"related_works":["https://openalex.org/W3131709275","https://openalex.org/W3005491711","https://openalex.org/W3037580942","https://openalex.org/W3146777637","https://openalex.org/W3105242324","https://openalex.org/W2791647162","https://openalex.org/W2796156786","https://openalex.org/W3011209123","https://openalex.org/W3177999760","https://openalex.org/W2964309797","https://openalex.org/W3008675085","https://openalex.org/W3095012670","https://openalex.org/W2916685081","https://openalex.org/W2963964591","https://openalex.org/W3161127957","https://openalex.org/W2769639994","https://openalex.org/W2950961956","https://openalex.org/W3037057938","https://openalex.org/W2743923735","https://openalex.org/W3104842308"],"abstract_inverted_index":{"Acoustic":[0],"word":[1,123,127,207],"embeddings":[2,11,48],"are":[3,190],"fixed-dimensional":[4],"representations":[5],"of":[6,96,135,151],"variable-length":[7],"speech":[8,17,25,35],"segments.":[9],"Such":[10],"can":[12],"form":[13],"the":[14,37,93,144,165,175,202,215],"basis":[15],"for":[16],"search,":[18],"indexing":[19],"and":[20,72,108,114,211],"discovery":[21],"systems":[22],"when":[23],"conventional":[24],"recognition":[26],"is":[27,36,185],"not":[28],"possible.":[29],"In":[30,125],"zero-resource":[31,78,145],"settings":[32],"where":[33],"unlabelled":[34],"only":[38,160],"available":[39],"resource,":[40],"we":[41,54,58],"need":[42],"a":[43,60,89,100,115,126,161],"method":[44],"that":[45,201],"gives":[46],"robust":[47],"on":[49,65,92,130,143,192],"an":[50],"arbitrary":[51],"language.":[52],"Here":[53],"explore":[55],"multilingual":[56,83,166,177,217],"transfer:":[57],"train":[59],"single":[61],"supervised":[62],"embedding":[63],"model":[64],"labelled":[66],"data":[67],"from":[68,111],"multiple":[69,112],"well-resourced":[70],"languages":[71,146,174,184],"then":[73],"apply":[74],"it":[75],"to":[76,104,121],"unseen":[77],"languages.":[79,194],"We":[80,195],"consider":[81],"three":[82],"recurrent":[84],"neural":[85],"network":[86],"(RNN)":[87],"models:":[88],"classifier":[90],"trained":[91,103,120,142],"joint":[94],"vocabularies":[95],"all":[97,134],"training":[98,163,173,183],"languages;":[99,113],"Siamese":[101],"RNN":[102,119],"discriminate":[105],"between":[106],"same":[107],"different":[109],"words":[110],"correspondence":[116],"autoencoder":[117],"(CAE)":[118],"reconstruct":[122],"pairs.":[124],"discrimination":[128],"task":[129],"six":[131],"target":[132],"languages,":[133,164],"these":[136],"models":[137,141,178],"outperform":[138],"state-of-the-art":[139],"unsupervised":[140],"themselves,":[147],"giving":[148],"relative":[149],"improvements":[150,189],"more":[152,172,182,205],"than":[153,214],"30%":[154],"in":[155],"average":[156],"precision.":[157],"When":[158],"using":[159],"few":[162],"CAE-RNN":[167,203],"performs":[168],"better,":[169],"but":[170,188],"with":[171],"other":[176,216],"perform":[179],"similarly.":[180],"Using":[181],"generally":[186],"beneficial,":[187],"marginal":[191],"some":[193],"present":[196],"probing":[197],"experiments":[198],"which":[199],"show":[200],"encodes":[204],"phonetic,":[206],"duration,":[208],"language":[209],"identity":[210],"speaker":[212],"information":[213],"models.":[218]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}