{"id":"https://openalex.org/W4412944958","doi":"https://doi.org/10.18653/v1/2025.acl-long.961","title":"ZIPA: A family of efficient models for multilingual phone recognition","display_name":"ZIPA: A family of efficient models for multilingual phone recognition","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944958","doi":"https://doi.org/10.18653/v1/2025.acl-long.961"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.961","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.961","pdf_url":"https://aclanthology.org/2025.acl-long.961.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.961.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100370161","display_name":"Jianguo Zhu","orcid":"https://orcid.org/0000-0002-9763-4047"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jian Zhu","raw_affiliation_strings":["University of British Columbia University of British Columbia University of Zurich Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia University of British Columbia University of Zurich Carnegie Mellon University","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086887575","display_name":"Farhan Samir","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Farhan Samir","raw_affiliation_strings":["University of British Columbia University of British Columbia University of Zurich Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia University of British Columbia University of Zurich Carnegie Mellon University","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041778529","display_name":"Eleanor Chodroff","orcid":"https://orcid.org/0000-0003-4549-5919"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Eleanor Chodroff","raw_affiliation_strings":["University of British Columbia University of British Columbia University of Zurich Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia University of British Columbia University of Zurich Carnegie Mellon University","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059859009","display_name":"David R. Mortensen","orcid":"https://orcid.org/0000-0002-3927-6851"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"David R. Mortensen","raw_affiliation_strings":["University of British Columbia University of British Columbia University of Zurich Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia University of British Columbia University of Zurich Carnegie Mellon University","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I141945490"],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83715034,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"19568","last_page":"19585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9929999709129333,"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":0.9929999709129333,"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":0.9361000061035156,"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":0.9290000200271606,"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/phone","display_name":"Phone","score":0.7851147651672363},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7065114974975586},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5338365435600281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3643304109573364},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34527644515037537},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.05078527331352234}],"concepts":[{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7851147651672363},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7065114974975586},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5338365435600281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3643304109573364},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34527644515037537},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.05078527331352234},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.961","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.961","pdf_url":"https://aclanthology.org/2025.acl-long.961.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:doi:10.5167/uzh-292807","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferenceItem"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.961","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.961","pdf_url":"https://aclanthology.org/2025.acl-long.961.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320331257","display_name":"Alliance de recherche num\u00e9rique du Canada","ror":"https://ror.org/010r6td27"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944958.pdf","grobid_xml":"https://content.openalex.org/works/W4412944958.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W3149968464"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W2061937230"],"abstract_inverted_index":{"We":[0],"present":[1],"ZIPA,":[2,48],"a":[3,21,34],"family":[4],"of":[5,14,29,79],"efficient":[6,58],"speech":[7,24],"models":[8],"that":[9],"advances":[10],"the":[11,44,57],"state-of-the-art":[12],"performance":[13,89],"crosslinguistic":[15],"phone":[16,31,64],"recognition.We":[17],"first":[18],"curated":[19],"IPAPACK++,":[20],"large-scale":[22,45],"multilingual":[23,81],"corpus":[25],"with":[26,67],"17,132":[27],"hours":[28,78],"normalized":[30],"transcriptions":[32],"and":[33,41,52,61],"novel":[35],"evaluation":[36],"set":[37],"capturing":[38],"unseen":[39],"languages":[40],"sociophonetic":[42,99],"variation.With":[43],"training":[46,75],"data,":[47],"including":[49],"transducer":[50],"(ZIPA-T)":[51],"CTC-based":[53],"(ZIPA-CR)":[54],"variants,":[55],"leverage":[56],"Zipformer":[59],"backbones":[60],"outperform":[62],"existing":[63],"recognition":[65],"systems":[66],"much":[68],"fewer":[69],"parameters.Further":[70],"scaling":[71],"via":[72],"noisy":[73],"student":[74],"on":[76,90],"11,000":[77],"pseudo-labeled":[80],"data":[82],"yields":[83],"further":[84],"improvement.While":[85],"ZIPA":[86],"achieves":[87],"strong":[88],"benchmarks,":[91],"error":[92],"analysis":[93],"reveals":[94],"persistent":[95],"limitations":[96],"in":[97],"modeling":[98],"diversity,":[100],"underscoring":[101],"challenges":[102],"for":[103],"future":[104],"research.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}