{"id":"https://openalex.org/W3005491711","doi":"https://doi.org/10.1109/icassp40776.2020.9054202","title":"Multilingual Acoustic Word Embedding Models for Processing Zero-resource Languages","display_name":"Multilingual Acoustic Word Embedding Models for Processing Zero-resource Languages","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3005491711","doi":"https://doi.org/10.1109/icassp40776.2020.9054202","mag":"3005491711"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.02109","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":true,"raw_author_name":"Herman Kamper","raw_affiliation_strings":["E&E Engineering, Stellenbosch University","StellenBosch University"],"affiliations":[{"raw_affiliation_string":"E&E Engineering, Stellenbosch University","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","University of Edinburgh,"],"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh","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","University of Edinburgh,"],"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh","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":3,"corresponding_author_ids":["https://openalex.org/A5040305929"],"corresponding_institution_ids":["https://openalex.org/I26092322"],"apc_list":null,"apc_paid":null,"fwci":0.1371,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52450179,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"6414","last_page":"6418"},"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":0.9991999864578247,"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":0.9988999962806702,"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":0.7561808824539185},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6409635543823242},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6372839212417603},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6207462549209595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5757473707199097},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4960063397884369},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4949302077293396},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.48960262537002563},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.47327375411987305},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47017520666122437},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3978593647480011},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1263836920261383},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10816675424575806}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7561808824539185},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6409635543823242},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6372839212417603},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6207462549209595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5757473707199097},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4960063397884369},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4949302077293396},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.48960262537002563},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.47327375411987305},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47017520666122437},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3978593647480011},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1263836920261383},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10816675424575806},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2002.02109","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.02109","pdf_url":"https://arxiv.org/pdf/2002.02109","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:publications/bb79f7c9-4bd8-43f8-9648-326839919406","is_oa":true,"landing_page_url":"https://ieeexplore.ieee.org/document/9054202","pdf_url":"https://www.research.ed.ac.uk/en/publications/bb79f7c9-4bd8-43f8-9648-326839919406","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 2020, Multilingual Acoustic Word Embedding Models for Processing Zero-Resource Languages. in ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 6414-6418, 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, Barcelona, Spain, 4/05/20. https://doi.org/10.1109/ICASSP40776.2020.9054202","raw_type":"contributionToPeriodical"},{"id":"mag:3005491711","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2002.02109.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":"pmh:oai:pure.ed.ac.uk:openaire/bb79f7c9-4bd8-43f8-9648-326839919406","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/bb79f7c9-4bd8-43f8-9648-326839919406","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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 2020, Multilingual Acoustic Word Embedding Models for Processing Zero-Resource Languages. in ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 6414-6418, 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, Barcelona, Spain, 4/05/20. https://doi.org/10.1109/ICASSP40776.2020.9054202","raw_type":"contributionToPeriodical"},{"id":"doi:10.48550/arxiv.2002.02109","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.02109","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":"article"},{"id":"doi:10.17023/ff8t-hm72","is_oa":true,"landing_page_url":"https://doi.org/10.17023/ff8t-hm72","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.02109","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.02109","pdf_url":"https://arxiv.org/pdf/2002.02109","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":[{"id":"https://metadata.un.org/sdg/10","score":0.5400000214576721,"display_name":"Reduced inequalities"}],"awards":[{"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"}],"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/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":49,"referenced_works":["https://openalex.org/W1778492285","https://openalex.org/W1924770834","https://openalex.org/W1970890968","https://openalex.org/W2025482506","https://openalex.org/W2057007397","https://openalex.org/W2059652594","https://openalex.org/W2072054026","https://openalex.org/W2084534958","https://openalex.org/W2157331557","https://openalex.org/W2165698076","https://openalex.org/W2166681504","https://openalex.org/W2171019095","https://openalex.org/W2190506272","https://openalex.org/W2291770225","https://openalex.org/W2346964103","https://openalex.org/W2407151108","https://openalex.org/W2550241133","https://openalex.org/W2578392894","https://openalex.org/W2614542633","https://openalex.org/W2758697525","https://openalex.org/W2769437540","https://openalex.org/W2802557066","https://openalex.org/W2884305338","https://openalex.org/W2889313720","https://openalex.org/W2894835365","https://openalex.org/W2900840356","https://openalex.org/W2916113431","https://openalex.org/W2927191280","https://openalex.org/W2933976917","https://openalex.org/W2962736743","https://openalex.org/W2963259843","https://openalex.org/W2963425185","https://openalex.org/W2963431393","https://openalex.org/W2963571336","https://openalex.org/W2963620343","https://openalex.org/W2963720603","https://openalex.org/W2963879199","https://openalex.org/W2964169922","https://openalex.org/W2964309797","https://openalex.org/W2972764223","https://openalex.org/W2973096781","https://openalex.org/W3105242324","https://openalex.org/W6640212811","https://openalex.org/W6697293080","https://openalex.org/W6729855024","https://openalex.org/W6735305794","https://openalex.org/W6746041127","https://openalex.org/W6755235688","https://openalex.org/W6786045457"],"related_works":["https://openalex.org/W3015325583","https://openalex.org/W3033831118","https://openalex.org/W3146777637","https://openalex.org/W3037580942","https://openalex.org/W3105242324","https://openalex.org/W3011209123","https://openalex.org/W2964309797","https://openalex.org/W2791647162","https://openalex.org/W2963340922","https://openalex.org/W3104842308","https://openalex.org/W3177999760","https://openalex.org/W2916685081","https://openalex.org/W3150635893","https://openalex.org/W3037057938","https://openalex.org/W2796156786","https://openalex.org/W2964102148","https://openalex.org/W2262099980","https://openalex.org/W2938309556","https://openalex.org/W3095012670","https://openalex.org/W2584414011"],"abstract_inverted_index":{"Acoustic":[0],"word":[1,90,97],"embeddings":[2,21],"are":[3],"fixed-dimensional":[4],"representations":[5],"of":[6,79],"variable-length":[7],"speech":[8,14,27],"segments.":[9],"In":[10],"settings":[11],"where":[12],"unlabelled":[13],"is":[15],"the":[16,76,121,130,140],"only":[17],"available":[18],"resource,":[19],"such":[20],"can":[22],"be":[23],"used":[24],"in":[25],"\"zero-resource\"":[26],"search,":[28],"indexing":[29],"and":[30,50,83,115],"discovery":[31],"systems.":[32],"Here":[33],"we":[34,63],"propose":[35],"to":[36,54,88],"train":[37],"a":[38,71,84,96,126],"single":[39,127],"supervised":[40],"embedding":[41],"model":[42,132],"on":[43,75,100,107,120,139],"labelled":[44],"data":[45],"from":[46],"multiple":[47],"well-resourced":[48,109],"languages":[49],"then":[51],"apply":[52],"it":[53],"unseen":[55],"zero-resource":[56,103,122],"languages.":[57,104,123],"For":[58],"this":[59],"transfer":[60],"learning":[61],"approach,":[62],"consider":[64],"two":[65],"multilingual":[66],"recurrent":[67],"neural":[68],"network":[69],"models:":[70],"discriminative":[72],"classifier":[73],"trained":[74,87,106,119],"joint":[77],"vocabularies":[78],"all":[80],"training":[81,128],"languages,":[82,110],"correspondence":[85],"autoencoder":[86],"reconstruct":[89],"pairs.":[91],"We":[92],"test":[93],"these":[94],"using":[95],"discrimination":[98],"task":[99],"six":[101],"target":[102],"When":[105],"seven":[108],"both":[111],"models":[112,118],"perform":[113],"similarly":[114],"outperform":[116],"unsupervised":[117],"With":[124],"just":[125],"language,":[129],"second":[131],"works":[133],"better,":[134],"but":[135],"performance":[136],"depends":[137],"more":[138],"particular":[141],"training-testing":[142],"language":[143],"pair.":[144]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}