{"id":"https://openalex.org/W4385823106","doi":"https://doi.org/10.21437/interspeech.2023-268","title":"Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Pooling","display_name":"Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Pooling","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823106","doi":"https://doi.org/10.21437/interspeech.2023-268"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-268","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/files/352043756/Acoustic_word_SANABRIA_DOA17052023_AFV_CC_BY.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053704856","display_name":"Ramon Sanabria","orcid":null},"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":true,"raw_author_name":"Ramon Sanabria","raw_affiliation_strings":["The University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"The University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044666169","display_name":"Ond\u0159ej Klejch","orcid":"https://orcid.org/0000-0001-5495-967X"},"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":"Ond\u0159ej Klejch","raw_affiliation_strings":["The University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"The University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100662187","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-2445-2605"},"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":"Hao Tang","raw_affiliation_strings":["The University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"The 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":["The University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"The University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053704856"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09829925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"406","last_page":"410"},"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":0.9998000264167786,"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":0.9983000159263611,"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/pooling","display_name":"Pooling","score":0.9292673468589783},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8006769418716431},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7411088347434998},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7042292356491089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6205494999885559},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.581121563911438},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5465863943099976},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.500507116317749},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.47445496916770935},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10055333375930786},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06950938701629639}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.9292673468589783},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8006769418716431},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7411088347434998},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7042292356491089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6205494999885559},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.581121563911438},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5465863943099976},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.500507116317749},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.47445496916770935},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10055333375930786},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06950938701629639},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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":3,"locations":[{"id":"doi:10.21437/interspeech.2023-268","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/502c336f-9401-468a-be5b-0e3f8f07c940","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/502c336f-9401-468a-be5b-0e3f8f07c940","pdf_url":"https://www.research.ed.ac.uk/files/352043756/Acoustic_word_SANABRIA_DOA17052023_AFV_CC_BY.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sanabria, R, Klejch, O, Tang, H & Goldwater, S 2023, Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Pooling. in Proc. INTERSPEECH 2023. Interspeech, International Speech Communication Association, pp. 406-410, Interspeech 2023, Dublin, Ireland, 20/08/23. https://doi.org/10.21437/Interspeech.2023-268","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/502c336f-9401-468a-be5b-0e3f8f07c940","is_oa":true,"landing_page_url":"https://www.isca-speech.org/archive/interspeech_2023/sanabria23_interspeech.html","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sanabria, R, Klejch, O, Tang, H & Goldwater, S 2023, Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Pooling. in Proc. INTERSPEECH 2023. Interspeech, International Speech Communication Association, pp. 406-410, Interspeech 2023, Dublin, Ireland, 20/08/23. https://doi.org/10.21437/Interspeech.2023-268","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/502c336f-9401-468a-be5b-0e3f8f07c940","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/502c336f-9401-468a-be5b-0e3f8f07c940","pdf_url":"https://www.research.ed.ac.uk/files/352043756/Acoustic_word_SANABRIA_DOA17052023_AFV_CC_BY.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sanabria, R, Klejch, O, Tang, H & Goldwater, S 2023, Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Pooling. in Proc. INTERSPEECH 2023. Interspeech, International Speech Communication Association, pp. 406-410, Interspeech 2023, Dublin, Ireland, 20/08/23. https://doi.org/10.21437/Interspeech.2023-268","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4300000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385823106.pdf","grobid_xml":"https://content.openalex.org/works/W4385823106.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W66627554","https://openalex.org/W148837159","https://openalex.org/W2057007397","https://openalex.org/W2059652594","https://openalex.org/W2173629880","https://openalex.org/W2407151108","https://openalex.org/W2468716020","https://openalex.org/W2514741789","https://openalex.org/W2584414011","https://openalex.org/W2913062184","https://openalex.org/W2950133079","https://openalex.org/W2963242190","https://openalex.org/W2963720603","https://openalex.org/W2998702515","https://openalex.org/W3005680577","https://openalex.org/W3034238904","https://openalex.org/W3036601975","https://openalex.org/W3044967013","https://openalex.org/W3095410713","https://openalex.org/W3110761489","https://openalex.org/W3146777637","https://openalex.org/W3150635893","https://openalex.org/W3198429080","https://openalex.org/W3198712558","https://openalex.org/W3209059054","https://openalex.org/W3214697273","https://openalex.org/W4221154554","https://openalex.org/W4223486244","https://openalex.org/W4297841660","https://openalex.org/W4300047444","https://openalex.org/W4310348293","https://openalex.org/W4375869060"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W2061937230"],"abstract_inverted_index":{"Acoustic":[0],"word":[1,107],"embeddings":[2],"are":[3,20],"typically":[4],"created":[5],"by":[6],"training":[7,89],"a":[8,34,42,78,103,128],"pooling":[9,91,134],"function":[10],"using":[11,22],"pairs":[12,87],"of":[13,115,137],"word-like":[14],"units.":[15],"For":[16],"unsupervised":[17],"systems,":[18],"these":[19],"mined":[21],"k-nearest":[23],"neighbor":[24],"(KNN)":[25],"search,":[26],"which":[27],"is":[28,113,121],"slow.":[29],"Recently,":[30],"mean-pooled":[31],"representations":[32],"from":[33,131],"pre-trained":[35,140],"self-supervised":[36,69],"English":[37],"model":[38,70],"were":[39],"suggested":[40],"as":[41],"promising":[43],"alternative,":[44],"but":[45],"their":[46],"performance":[47],"on":[48,94,106,135],"target":[49,73],"languages":[50],"was":[51],"not":[52],"fully":[53],"competitive.":[54],"Here,":[55],"we":[56,62,76,97],"explore":[57],"improvements":[58],"to":[59,66,71,83],"both":[60,100],"approaches:":[61],"use":[63,77],"continued":[64,139],"pre-training":[65],"adapt":[67],"the":[68,72,90,110,138],"language,":[74],"and":[75,120],"multilingual":[79],"phone":[80,85],"recognizer":[81],"(MPR)":[82],"mine":[84],"n-gram":[86],"for":[88],"function.":[92],"Evaluating":[93],"four":[95],"languages,":[96],"show":[98,127],"that":[99],"methods":[101],"outperform":[102],"recent":[104],"approach":[105],"discrimination.":[108],"Moreover,":[109],"MPR":[111],"method":[112],"orders":[114],"magnitude":[116],"faster":[117],"than":[118],"KNN,":[119],"highly":[122],"data":[123],"efficient.":[124],"We":[125],"also":[126],"small":[129],"improvement":[130],"performing":[132],"learned":[133],"top":[136],"representations.":[141]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}