{"id":"https://openalex.org/W4221166827","doi":"https://doi.org/10.1109/icassp43922.2022.9747131","title":"Unified Multimodal Punctuation Restoration Framework for Mixed-Modality Corpus","display_name":"Unified Multimodal Punctuation Restoration Framework for Mixed-Modality Corpus","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221166827","doi":"https://doi.org/10.1109/icassp43922.2022.9747131"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747131","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041011296","display_name":"Yaoming Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaoming Zhu","raw_affiliation_strings":["ByteDance AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675839","display_name":"Liwei Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liwei Wu","raw_affiliation_strings":["ByteDance AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046413480","display_name":"Shanbo Cheng","orcid":"https://orcid.org/0000-0002-6115-9483"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shanbo Cheng","raw_affiliation_strings":["ByteDance AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101693712","display_name":"Mingxuan Wang","orcid":"https://orcid.org/0009-0000-9738-4263"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingxuan Wang","raw_affiliation_strings":["ByteDance AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7272","last_page":"7276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":0.9998999834060669,"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":0.9984999895095825,"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","display_name":"Punctuation","score":0.8086968660354614},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7323414087295532},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6933804750442505},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5352044701576233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39011090993881226}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.8086968660354614},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7323414087295532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6933804750442505},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5352044701576233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39011090993881226}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747131","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W40475138","https://openalex.org/W1522301498","https://openalex.org/W2169187092","https://openalex.org/W2194775991","https://openalex.org/W2398104528","https://openalex.org/W2705373224","https://openalex.org/W2806626660","https://openalex.org/W2888942278","https://openalex.org/W2896457183","https://openalex.org/W2899902398","https://openalex.org/W2933138175","https://openalex.org/W2937326859","https://openalex.org/W2938722449","https://openalex.org/W2962989741","https://openalex.org/W3010663975","https://openalex.org/W3036601975","https://openalex.org/W3037101098","https://openalex.org/W3092085609","https://openalex.org/W3094965760","https://openalex.org/W3160489181","https://openalex.org/W3163457913","https://openalex.org/W3197771105","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6751513048","https://openalex.org/W6755207826","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2936002343","https://openalex.org/W2188883480","https://openalex.org/W1592364192","https://openalex.org/W656840002","https://openalex.org/W1605117403","https://openalex.org/W2381416480","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"punctuation":[1,17,53],"restoration":[2,54],"task":[3],"aims":[4],"to":[5,29,58,141],"correctly":[6],"punctuate":[7,59,142],"the":[8,25,60,82,96,99,144],"output":[9],"transcriptions":[10],"of":[11,41,92,98],"automatic":[12],"speech":[13],"recognition":[14],"systems.":[15],"Previous":[16],"models,":[18,137],"either":[19],"using":[20],"text":[21],"only":[22],"or":[23],"demanding":[24],"corresponding":[26],"audio,":[27],"tend":[28],"be":[30],"constrained":[31],"by":[32,112,133],"real":[33],"scenes,":[34],"where":[35],"unpunctuated":[36],"sentences":[37,62],"are":[38],"a":[39,50,64,75,85,120,130],"mixture":[40],"those":[42],"with":[43,63],"and":[44,71,88],"without":[45],"audio.":[46],"This":[47],"paper":[48],"proposes":[49],"unified":[51],"multimodal":[52],"framework,":[55],"named":[56],"UniPunc,":[57],"mixed":[61,145],"single":[65],"model.":[66],"UniPunc":[67,100,138],"jointly":[68],"represents":[69],"audio":[70],"non-audio":[72],"samples":[73],"in":[74],"shared":[76],"latent":[77],"space,":[78],"based":[79],"on":[80,101,143],"which":[81,104],"model":[83],"learns":[84],"hybrid":[86],"representation":[87],"punctuates":[89],"both":[90],"kinds":[91],"samples.":[93],"We":[94],"validate":[95],"effectiveness":[97],"real-world":[102],"datasets,":[103],"outperforms":[105],"various":[106],"strong":[107],"baselines":[108],"(e.g.":[109],"BERT,":[110],"MuSe)":[111],"at":[113,151],"least":[114],"0.8":[115],"overall":[116],"F1":[117],"scores,":[118],"making":[119],"new":[121],"state-of-the-art.":[122],"Extensive":[123],"experiments":[124],"show":[125],"that":[126],"UniPunc\u2019s":[127],"design":[128],"is":[129,149],"pervasive":[131],"solution:":[132],"grafting":[134],"onto":[135],"previous":[136],"enables":[139],"them":[140],"corpus.":[146],"Our":[147],"code":[148],"available":[150],"github.com/Yaoming95/UniPunc":[152]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}