{"id":"https://openalex.org/W4412945262","doi":"https://doi.org/10.18653/v1/2025.acl-long.592","title":"Phonotomizer: A Compact, Unsupervised, Online Training Approach to Real-Time, Multilingual Phonetic Segmentation","display_name":"Phonotomizer: A Compact, Unsupervised, Online Training Approach to Real-Time, Multilingual Phonetic Segmentation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945262","doi":"https://doi.org/10.18653/v1/2025.acl-long.592"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.592","doi":"https://doi.org/10.18653/v1/2025.acl-long.592","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.592","pdf_url":"https://aclanthology.org/2025.acl-long.592.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2025.acl-long.592.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053269429","display_name":"Michael S. Yantosca","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael S. Yantosca","raw_affiliation_strings":["Department of Computer Science University of Houston Houston , TX , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Houston Houston , TX , USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001205166","display_name":"Albert M. K. Cheng","orcid":"https://orcid.org/0000-0003-2134-3056","observed_orcids":["https://orcid.org/0000-0003-2134-3056"]},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Albert M. K. Cheng","raw_affiliation_strings":["Department of Computer Science University of Houston Houston , TX , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Houston Houston , TX , USA","institution_ids":["https://openalex.org/I44461941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I44461941"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16030043,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12135","last_page":"12147"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955999851226807,"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":0.9955999851226807,"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/T10860","display_name":"Speech and Audio Processing","score":0.0017999999690800905,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0010999999940395355,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/phonetic-segmentation","display_name":"phonetic segmentation","score":0.8560000061988831},{"id":"https://openalex.org/keywords/multilingual-speech","display_name":"multilingual speech","score":0.7020000219345093},{"id":"https://openalex.org/keywords/unsupervised-training","display_name":"unsupervised training","score":0.7789999842643738},{"id":"https://openalex.org/keywords/online-training","display_name":"online training","score":0.9089999794960022},{"id":"https://openalex.org/keywords/real-time-speech-processing","display_name":"real-time speech processing","score":0.8629999756813049}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8106894493103027},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6353042125701904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5872650742530823},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.584480345249176},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46430471539497375},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.46050187945365906},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44949954748153687},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.592","doi":"https://doi.org/10.18653/v1/2025.acl-long.592","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.592","pdf_url":"https://aclanthology.org/2025.acl-long.592.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.592","doi":"https://doi.org/10.18653/v1/2025.acl-long.592","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.592","pdf_url":"https://aclanthology.org/2025.acl-long.592.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945262.pdf","grobid_xml":"https://content.openalex.org/works/W4412945262.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6931563661","https://openalex.org/W6950536077","https://openalex.org/W2216348618","https://openalex.org/W2403055070","https://openalex.org/W2408737549","https://openalex.org/W7217444968","https://openalex.org/W3085206017","https://openalex.org/W170586818","https://openalex.org/W7029126912","https://openalex.org/W7218000632"],"abstract_inverted_index":{"Phonetic":[0],"transcription":[1],"requires":[2],"significant":[3],"time":[4],"and":[5,17,77,85,102],"expert":[6],"training.Automated,":[7],"state-of-theart":[8],"text-dependent":[9],"methods":[10],"still":[11],"involve":[12],"substantial":[13],"pre-training":[14],"annotation":[15],"labor":[16],"may":[18],"not":[19],"generalize":[20],"to":[21,43,57,93],"multiple":[22],"languages.Hallucination":[23],"of":[24],"speech":[25],"amid":[26],"silence":[27],"or":[28],"non-speech":[29],"noise":[30],"can":[31,78],"also":[32],"plague":[33],"these":[34],"methods,":[35],"which":[36],"fall":[37],"short":[38],"in":[39,66],"real-time":[40],"applications":[41],"due":[42],"post":[44],"hoc":[45],"whole-phrase":[46],"evaluation.This":[47],"paper":[48],"introduces":[49],"Phonotomizer,":[50],"a":[51,62],"compact,":[52],"unsupervised,":[53],"online":[54],"training":[55,104],"approach":[56],"automatic,":[58],"multilingual":[59],"phonetic":[60],"segmentation,":[61],"critical":[63],"first":[64],"stage":[65],"transcription.Unlike":[67],"prior":[68],"approaches,":[69],"Phonotomizer":[70],"trains":[71],"on":[72,83],"raw":[73],"sound":[74],"files":[75],"alone":[76],"modulate":[79],"computational":[80],"exactness.Preliminary":[81],"evaluations":[82],"Irish":[84],"Twi,":[86],"two":[87],"underrepresented":[88],"languages,":[89],"exhibit":[90],"segmentation":[91],"comparable":[92],"current":[94],"forced":[95],"alignment":[96],"technology,":[97],"reducing":[98],"acoustic":[99],"model":[100],"size":[101],"minimizing":[103],"epochs.":[105]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2025-10-10T00:00:00"}