{"id":"https://openalex.org/W7126436239","doi":"https://doi.org/10.18653/v1/2024.unimplicit-1.3","title":"Resolving Transcription Ambiguity in Spanish: A Hybrid Acoustic-Lexical System for Punctuation Restoration","display_name":"Resolving Transcription Ambiguity in Spanish: A Hybrid Acoustic-Lexical System for Punctuation Restoration","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126436239","doi":"https://doi.org/10.18653/v1/2024.unimplicit-1.3"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.unimplicit-1.3","doi":"https://doi.org/10.18653/v1/2024.unimplicit-1.3","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.unimplicit-1.3","pdf_url":"https://aclanthology.org/2024.unimplicit-1.3.pdf","source":{"id":"https://openalex.org/S7407121461","display_name":"Workshop on Understanding Implicit and Underspecified Language (UnImplicit)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 Third Workshop on Understanding Implicit and Underspecified Language","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2024.unimplicit-1.3.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033209447","display_name":"Xiliang Zhu","orcid":"https://orcid.org/0000-0001-9351-3005","observed_orcids":["https://orcid.org/0000-0001-9351-3005"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiliang Zhu","raw_affiliation_strings":["Dialpad Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dialpad Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065914366","display_name":"Chia-Tien Chang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chia-Tien Chang","raw_affiliation_strings":["Dialpad Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dialpad Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044490934","display_name":"Shayna Gardiner","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shayna Gardiner","raw_affiliation_strings":["Dialpad Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dialpad Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153504513","display_name":"David Rossouw","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Rossouw","raw_affiliation_strings":["Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027756293","display_name":"Jonas Robertson","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonas Robertson","raw_affiliation_strings":["Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inc","institution_ids":[]}]}],"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":0.37818584,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"41"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9916999936103821,"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":0.9916999936103821,"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":0.004800000227987766,"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/T12031","display_name":"Speech and dialogue systems","score":0.002099999925121665,"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/punctuation-restoration","display_name":"punctuation restoration","score":0.9869999885559082},{"id":"https://openalex.org/keywords/conversational-speech","display_name":"conversational speech","score":0.6779999732971191},{"id":"https://openalex.org/keywords/large-language-models-comparison","display_name":"large language models comparison","score":0.675000011920929}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.6051999926567078},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5751000046730042},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5295000076293945},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5131999850273132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4375999867916107},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33309999108314514},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.24330000579357147},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24009999632835388},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2150000035762787}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2024.unimplicit-1.3","doi":"https://doi.org/10.18653/v1/2024.unimplicit-1.3","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.unimplicit-1.3","pdf_url":"https://aclanthology.org/2024.unimplicit-1.3.pdf","source":{"id":"https://openalex.org/S7407121461","display_name":"Workshop on Understanding Implicit and Underspecified Language (UnImplicit)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 Third Workshop on Understanding Implicit and Underspecified Language","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2402.03519","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.03519","pdf_url":"https://arxiv.org/pdf/2402.03519","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2402.03519","doi":"https://doi.org/10.48550/arxiv.2402.03519","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.03519","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.unimplicit-1.3","doi":"https://doi.org/10.18653/v1/2024.unimplicit-1.3","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.unimplicit-1.3","pdf_url":"https://aclanthology.org/2024.unimplicit-1.3.pdf","source":{"id":"https://openalex.org/S7407121461","display_name":"Workshop on Understanding Implicit and Underspecified Language (UnImplicit)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 Third Workshop on Understanding Implicit and Underspecified Language","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126436239.pdf","grobid_xml":"https://content.openalex.org/works/W7126436239.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4287889742","https://openalex.org/W4210452164","https://openalex.org/W3037230560","https://openalex.org/W4221166827","https://openalex.org/W7140079101","https://openalex.org/W4385822993","https://openalex.org/W4408353391","https://openalex.org/W3203803655","https://openalex.org/W3214450008","https://openalex.org/W4386429885"],"abstract_inverted_index":{"Punctuation":[0],"restoration":[1,30,54,87],"is":[2],"a":[3,49,66],"crucial":[4],"step":[5],"after":[6],"Automatic":[7],"Speech":[8],"Recognition":[9],"(ASR)":[10],"systems":[11],"to":[12],"enhance":[13],"transcript":[14],"readability":[15],"and":[16,43,62,84,91,112],"facilitate":[17],"subsequent":[18],"NLP":[19],"tasks.Nevertheless,":[20],"conventional":[21],"lexical-based":[22],"approaches":[23],"are":[24],"inadequate":[25],"for":[26,56],"solving":[27],"the":[28,73,104,117,123],"punctuation":[29,53,86],"task":[31],"in":[32,109],"Spanish,":[33],"where":[34],"ambiguity":[35],"can":[36,76],"be":[37],"often":[38],"found":[39],"between":[40],"unpunctuated":[41],"declaratives":[42],"questions.In":[44],"this":[45],"study,":[46],"we":[47,114],"propose":[48],"novel":[50],"hybrid":[51],"acoustic-lexical":[52],"system":[55,75],"Spanish":[57,93],"transcription,":[58],"which":[59],"consolidates":[60],"acoustic":[61],"lexical":[63],"signals":[64],"through":[65],"modular":[67],"process.Our":[68],"experiment":[69],"results":[70],"show":[71],"that":[72,116],"proposed":[74,130],"effectively":[77],"improve":[78],"F1":[79],"score":[80],"of":[81,106,122],"question":[82],"marks":[83],"overall":[85],"on":[88],"both":[89],"public":[90],"internal":[92],"conversational":[94],"datasets.Additionally,":[95],"benchmark":[96],"comparison":[97],"against":[98],"LLMs":[99],"(Large":[100],"Language":[101],"Model)":[102],"indicates":[103],"superiority":[105],"our":[107,129],"approach":[108],"accuracy,":[110],"reliability":[111],"latency.Furthermore,":[113],"demonstrate":[115],"Word":[118],"Error":[119],"Rate":[120],"(WER)":[121],"ASR":[124],"module":[125],"also":[126],"benefits":[127],"from":[128],"system.":[131]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-02T00:00:00"}