{"id":"https://openalex.org/W7166828520","doi":"https://doi.org/10.18653/v1/2026.acl-long.813","title":"POWSM: A Phonetic Open Whisper-Style Speech Foundation Model","display_name":"POWSM: A Phonetic Open Whisper-Style Speech Foundation Model","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166828520","doi":"https://doi.org/10.18653/v1/2026.acl-long.813"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.813","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.813","pdf_url":"https://aclanthology.org/2026.acl-long.813.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 64th 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/2026.acl-long.813.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139733757","display_name":"Chin-Jou Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chin-Jou Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027404450","display_name":"Kalvin Chang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kalvin Chang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067162151","display_name":"Shikhar Bharadwaj","orcid":"https://orcid.org/0009-0003-7202-0502"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shikhar Bharadwaj","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110721529","display_name":"Eunjung Yeo","orcid":"https://orcid.org/0009-0003-4452-4084"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eunjung Yeo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139827127","display_name":"Kwanghee Choi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kwanghee Choi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139781807","display_name":"Jian Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126976076","display_name":"David R. Mortensen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David R. Mortensen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139833411","display_name":"Shinji Watanabe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81817215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17882","last_page":"17899"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6693000197410583,"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":0.6693000197410583,"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/T10028","display_name":"Topic Modeling","score":0.048700001090765,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.04610000178217888,"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/foundation","display_name":"Foundation (evidence)","score":0.5006999969482422},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.32260000705718994},{"id":"https://openalex.org/keywords/acoustic-phonetics","display_name":"Acoustic phonetics","score":0.30090001225471497},{"id":"https://openalex.org/keywords/phonetics","display_name":"Phonetics","score":0.2759000062942505}],"concepts":[{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5365999937057495},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4805000126361847},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.374099999666214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35440000891685486},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31130000948905945},{"id":"https://openalex.org/C2781032008","wikidata":"https://www.wikidata.org/wiki/Q424083","display_name":"Acoustic phonetics","level":3,"score":0.30090001225471497},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2888999879360199},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.26759999990463257}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.813","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.813","pdf_url":"https://aclanthology.org/2026.acl-long.813.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.813","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.813","pdf_url":"https://aclanthology.org/2026.acl-long.813.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7839983701705933,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7291403024","display_name":null,"funder_award_id":"Bridges2","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320312143","display_name":"National Centre for Supercomputing Applications","ror":"https://ror.org/03r10zj06"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166828520.pdf","grobid_xml":"https://content.openalex.org/works/W7166828520.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Chin-Jou":[0],"Li,":[1],"Kalvin":[2],"Chang,":[3],"Shikhar":[4],"Bharadwaj,":[5],"Eunjung":[6],"Yeo,":[7],"Kwanghee":[8],"Choi,":[9],"Jian":[10],"Zhu,":[11],"David":[12],"R.":[13],"Mortensen,":[14],"Shinji":[15],"Watanabe.":[16],"Proceedings":[17],"of":[18,23],"the":[19,24],"64th":[20],"Annual":[21],"Meeting":[22],"Association":[25],"for":[26],"Computational":[27],"Linguistics":[28],"(Volume":[29],"1:":[30],"Long":[31],"Papers).":[32],"2026.":[33]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
