{"id":"https://openalex.org/W3025286576","doi":"https://doi.org/10.21437/interspeech.2020-2513","title":"That Sounds Familiar: An Analysis of Phonetic Representations Transfer Across Languages","display_name":"That Sounds Familiar: An Analysis of Phonetic Representations Transfer Across Languages","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3025286576","doi":"https://doi.org/10.21437/interspeech.2020-2513","mag":"3025286576"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2513","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2513","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.08118","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027217976","display_name":"Piotr \u017belasko","orcid":"https://orcid.org/0000-0002-8245-0413"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Piotr \u017belasko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069488212","display_name":"Laureano Moro-Vel\u00e1zquez","orcid":"https://orcid.org/0000-0002-3033-7005"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laureano Moro-Vel\u00e1zquez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048860892","display_name":"Odette Scharenborg","orcid":"https://orcid.org/0000-0003-0693-8852"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Odette Scharenborg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3705","last_page":"3709"},"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":0.9991000294685364,"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":0.9987000226974487,"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":0.8245944976806641},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.587712287902832},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5552074909210205},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5484082698822021},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4371185004711151},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43702441453933716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40513312816619873}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8245944976806641},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.587712287902832},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5552074909210205},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5484082698822021},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4371185004711151},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43702441453933716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40513312816619873},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2020-2513","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2513","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"},{"id":"pmh:oai:arXiv.org:2005.08118","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.08118","pdf_url":"https://arxiv.org/pdf/2005.08118","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:tudelft.nl:uuid:ea68435f-57a5-4472-b522-f8c90dbd218d","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:ea68435f-57a5-4472-b522-f8c90dbd218d","pdf_url":"http://resolver.tudelft.nl/uuid:ea68435f-57a5-4472-b522-f8c90dbd218d","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"},{"id":"mag:3025286576","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2005.08118.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.2005.08118","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.08118","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:2005.08118","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.08118","pdf_url":"https://arxiv.org/pdf/2005.08118","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":[{"score":0.8399999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W47568227","https://openalex.org/W66627554","https://openalex.org/W1992912377","https://openalex.org/W2085628288","https://openalex.org/W2088499802","https://openalex.org/W2094097435","https://openalex.org/W2152092236","https://openalex.org/W2164505566","https://openalex.org/W2295676751","https://openalex.org/W2526425061","https://openalex.org/W2786835190","https://openalex.org/W2962780374","https://openalex.org/W2963292011","https://openalex.org/W2972818416","https://openalex.org/W2990910192","https://openalex.org/W3015877095","https://openalex.org/W3045485643"],"related_works":["https://openalex.org/W3095732712","https://openalex.org/W3003382064","https://openalex.org/W148962591","https://openalex.org/W3160713074","https://openalex.org/W3008434450","https://openalex.org/W2767634090","https://openalex.org/W2123762975","https://openalex.org/W3008125272","https://openalex.org/W2901389167","https://openalex.org/W3015916194","https://openalex.org/W847337753","https://openalex.org/W261816329","https://openalex.org/W3135619128","https://openalex.org/W3096656663","https://openalex.org/W3135855479","https://openalex.org/W2122049569","https://openalex.org/W2166872825","https://openalex.org/W2991254485","https://openalex.org/W3093383192","https://openalex.org/W2112032806"],"abstract_inverted_index":{"Only":[0],"a":[1,39,61,79,87,95,144,175],"handful":[2],"of":[3,16,21,64,91,97,153],"the":[4,10,22,31,110,125,132,136,154,169,193],"world's":[5],"languages":[6,36,123,187],"are":[7,75,172],"abundant":[8],"with":[9],"resources":[11,32],"that":[12,83,167,171],"enable":[13],"practical":[14],"applications":[15],"speech":[17,42,195],"processing":[18],"technologies.":[19],"One":[20],"methods":[23],"to":[24,29,37,108,174],"overcome":[25],"this":[26,55],"problem":[27],"is":[28,106],"use":[30],"existing":[33],"in":[34,78,124,131],"other":[35,139,186],"train":[38],"multilingual":[40,80,99,126],"automatic":[41],"recognition":[43],"(ASR)":[44],"model,":[45,137],"which,":[46],"intuitively,":[47],"should":[48],"learn":[49],"some":[50],"universal":[51],"phonetic":[52],"representations.":[53],"In":[54],"work,":[56],"we":[57,85],"focus":[58],"on":[59],"gaining":[60],"deeper":[62],"understanding":[63],"how":[65,72],"general":[66],"these":[67],"representations":[68],"might":[69],"be,":[70],"and":[71,93,100,128],"individual":[73],"phones":[74,170],"getting":[76],"improved":[77],"setting.":[81],"To":[82],"end,":[84],"select":[86],"phonetically":[88],"diverse":[89],"set":[90],"languages,":[92],"perform":[94],"series":[96],"monolingual,":[98],"crosslingual":[101,133],"(zero-shot)":[102],"experiments.":[103],"The":[104],"ASR":[105,161],"trained":[107],"recognize":[109],"International":[111],"Phonetic":[112],"Alphabet":[113],"(IPA)":[114],"token":[115],"sequences.":[116],"We":[117],"observe":[118],"significant":[119],"improvements":[120],"across":[121],"all":[122],"setting,":[127,134],"stark":[129],"degradation":[130],"where":[135],"among":[138],"errors,":[140],"considers":[141],"Javanese":[142],"as":[143,148,150],"tone":[145],"language.":[146],"Notably,":[147],"little":[149],"10":[151],"hours":[152],"target":[155],"language":[156,177],"training":[157,183],"data":[158,184],"tremendously":[159],"reduces":[160],"error":[162],"rates.":[163],"Our":[164],"analysis":[165],"uncovered":[166],"even":[168],"unique":[173],"single":[176],"can":[178],"benefit":[179],"greatly":[180],"from":[181,185],"adding":[182],"-":[188],"an":[189],"encouraging":[190],"result":[191],"for":[192],"low-resource":[194],"community.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}