{"id":"https://openalex.org/W4322714819","doi":"https://doi.org/10.21437/interspeech.2022-60","title":"Simple and Effective Zero-shot Cross-lingual Phoneme Recognition","display_name":"Simple and Effective Zero-shot Cross-lingual Phoneme Recognition","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4322714819","doi":"https://doi.org/10.21437/interspeech.2022-60"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-60","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-60","pdf_url":"https://www.isca-archive.org/interspeech_2022/xu22b_interspeech.pdf","source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.isca-archive.org/interspeech_2022/xu22b_interspeech.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102647000","display_name":"Qiantong Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Qiantong Xu","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031979802","display_name":"Alexei Baevski","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Alexei Baevski","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083212922","display_name":"Michael Auli","orcid":"https://orcid.org/0000-0001-5974-4459"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Michael Auli","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":53,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2113","last_page":"2117"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9807999730110168,"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":0.9807999730110168,"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/simple","display_name":"Simple (philosophy)","score":0.7403577566146851},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6796209216117859},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6326494812965393},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5320075154304504},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4356686770915985},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35599613189697266},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.0784350335597992},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.062396109104156494}],"concepts":[{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.7403577566146851},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6796209216117859},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6326494812965393},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5320075154304504},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4356686770915985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35599613189697266},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0784350335597992},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.062396109104156494},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","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.2022-60","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-60","pdf_url":"https://www.isca-archive.org/interspeech_2022/xu22b_interspeech.pdf","source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2022-60","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-60","pdf_url":"https://www.isca-archive.org/interspeech_2022/xu22b_interspeech.pdf","source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4322714819.pdf","grobid_xml":"https://content.openalex.org/works/W4322714819.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W66627554","https://openalex.org/W2124509324","https://openalex.org/W2292087804","https://openalex.org/W2547875792","https://openalex.org/W2572670101","https://openalex.org/W2896457183","https://openalex.org/W2933138175","https://openalex.org/W2934852845","https://openalex.org/W2953190524","https://openalex.org/W2962799225","https://openalex.org/W2963292011","https://openalex.org/W2972943112","https://openalex.org/W2979476256","https://openalex.org/W2991213871","https://openalex.org/W2998284473","https://openalex.org/W3015877095","https://openalex.org/W3026041220","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3088761213","https://openalex.org/W3095410713","https://openalex.org/W3096032230","https://openalex.org/W3096338464","https://openalex.org/W3160525311","https://openalex.org/W3169320628","https://openalex.org/W3197223534","https://openalex.org/W3197278374","https://openalex.org/W3197845195","https://openalex.org/W3198429080","https://openalex.org/W3198712558","https://openalex.org/W4287068376","https://openalex.org/W4287173589","https://openalex.org/W4297808394","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4214877189","https://openalex.org/W2074502265","https://openalex.org/W2381179799","https://openalex.org/W4287637665","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2728912566","https://openalex.org/W2380471679","https://openalex.org/W2281347361"],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2,19],"self-training,":[3],"self-supervised":[4],"pretraining":[5],"and":[6,87],"unsupervised":[7],"learning":[8,45],"enabled":[9],"well":[10],"performing":[11],"speech":[12],"recognition":[13],"systems":[14],"without":[15],"any":[16],"labeled":[17,24],"data.However,":[18],"many":[20],"cases":[21],"there":[22],"is":[23,31,58],"data":[25],"available":[26],"for":[27],"related":[28],"languages":[29,66],"which":[30,83],"not":[32],"utilized":[33],"by":[34,46,60],"these":[35],"methods.This":[36],"paper":[37],"extends":[38],"previous":[39],"work":[40,82],"on":[41],"zero-shot":[42],"cross-lingual":[43],"transfer":[44],"fine-tuning":[47],"a":[48,92],"multilingually":[49],"pretrained":[50,94],"wav2vec":[51],"2.0":[52],"model":[53],"to":[54,67],"transcribe":[55],"unseen":[56],"languages.This":[57],"done":[59],"mapping":[61],"phonemes":[62],"of":[63,91],"the":[64,68],"training":[65],"target":[69],"language":[70],"using":[71],"articulatory":[72],"features.Experiments":[73],"show":[74],"that":[75],"this":[76],"simple":[77],"method":[78],"significantly":[79],"outperforms":[80],"prior":[81],"introduced":[84],"task-specific":[85],"architectures":[86],"used":[88],"only":[89],"part":[90],"monolingually":[93],"model.":[95]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}