{"id":"https://openalex.org/W4389988581","doi":"https://doi.org/10.1109/ictai59109.2023.00119","title":"Aligning Speakers: Evaluating and Visualizing Text-based Speaker Diarization Using Efficient Multiple Sequence Alignment","display_name":"Aligning Speakers: Evaluating and Visualizing Text-based Speaker Diarization Using Efficient Multiple Sequence Alignment","publication_year":2023,"publication_date":"2023-11-06","ids":{"openalex":"https://openalex.org/W4389988581","doi":"https://doi.org/10.1109/ictai59109.2023.00119"},"language":"en","primary_location":{"id":"doi:10.1109/ictai59109.2023.00119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictai59109.2023.00119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 35th International Conference on Tools with Artificial Intelligence (ICTAI)","raw_type":"proceedings-article"},"type":"article","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/A5100389824","display_name":"Chen Gong","orcid":"https://orcid.org/0000-0001-9305-6908"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chen Gong","raw_affiliation_strings":["Emory University,Department of Computer Science,Atlanta,GA,USA,30322"],"affiliations":[{"raw_affiliation_string":"Emory University,Department of Computer Science,Atlanta,GA,USA,30322","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105068598","display_name":"Peilin Wu","orcid":"https://orcid.org/0009-0008-9225-787X"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peilin Wu","raw_affiliation_strings":["Emory University,Department of Computer Science,Atlanta,GA,USA,30322"],"affiliations":[{"raw_affiliation_string":"Emory University,Department of Computer Science,Atlanta,GA,USA,30322","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101829031","display_name":"Jinho D. Choi","orcid":"https://orcid.org/0000-0003-2693-6934"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinho D. Choi","raw_affiliation_strings":["Emory University,Department of Computer Science,Atlanta,GA,USA,30322"],"affiliations":[{"raw_affiliation_string":"Emory University,Department of Computer Science,Atlanta,GA,USA,30322","institution_ids":["https://openalex.org/I150468666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100389824"],"corresponding_institution_ids":["https://openalex.org/I150468666"],"apc_list":null,"apc_paid":null,"fwci":0.1748,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58931956,"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":"778","last_page":"783"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.8381096720695496},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7568135261535645},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7327341437339783},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.508857250213623},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48671725392341614},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.47636792063713074},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.45145994424819946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43038254976272583},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4256126880645752},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2354333996772766}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8381096720695496},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7568135261535645},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7327341437339783},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.508857250213623},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48671725392341614},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.47636792063713074},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.45145994424819946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43038254976272583},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4256126880645752},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2354333996772766},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictai59109.2023.00119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictai59109.2023.00119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 35th International Conference on Tools with Artificial Intelligence (ICTAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2074231493","https://openalex.org/W2080213370","https://openalex.org/W2222512263","https://openalex.org/W2915347754","https://openalex.org/W3034999214","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3212886388","https://openalex.org/W4288089799","https://openalex.org/W4290771878","https://openalex.org/W4292779060","https://openalex.org/W4311000453","https://openalex.org/W4386794887","https://openalex.org/W6744711567","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6780218876","https://openalex.org/W6790122275","https://openalex.org/W6842194054","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1556857061","https://openalex.org/W2177420620","https://openalex.org/W4308671730","https://openalex.org/W4380994539","https://openalex.org/W2944691285","https://openalex.org/W3151768066"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,69,78],"novel":[4],"evaluation":[5],"approach":[6],"to":[7,62,67,96],"text-based":[8],"speaker":[9],"diarization":[10],"(SD),":[11],"tackling":[12],"the":[13,90,97,130,136],"limitations":[14],"of":[15,59,132,138],"traditional":[16],"metrics":[17,30,55],"that":[18,85],"do":[19],"not":[20],"account":[21],"for":[22,113,119],"any":[23],"contextual":[24],"information":[25],"in":[26,49,73,89,129],"text.":[27],"Two":[28],"new":[29],"are":[31],"proposed,":[32],"Text-based":[33],"Diarization":[34,38],"Error":[35],"Rate":[36],"and":[37,43,51,117,121],"F1,":[39],"which":[40,125],"perform":[41],"utterance-":[42],"word-level":[44],"evaluations":[45],"by":[46],"aligning":[47],"tokens":[48],"reference":[50,91],"hypothesis":[52,98],"transcripts.":[53],"Our":[54,102],"encompass":[56],"more":[57,70],"types":[58],"errors":[60],"compared":[61],"existing":[63],"ones,":[64],"allowing":[65],"us":[66],"make":[68],"comprehensive":[71],"analysis":[72],"SD.":[74],"To":[75],"align":[76],"tokens,":[77],"multiple":[79,87],"sequence":[80],"alignment":[81,95,115],"algorithm":[82,116],"is":[83,104],"introduced":[84],"supports":[86],"sequences":[88],"while":[92],"handling":[93],"high-dimensional":[94],"using":[99],"dynamic":[100],"programming.":[101],"work":[103],"packaged":[105],"into":[106],"two":[107],"tools,":[108],"align4d,":[109],"providing":[110],"an":[111],"API":[112],"our":[114],"TranscribeView":[118],"visualizing":[120],"evaluating":[122],"SD":[123],"errors,":[124],"can":[126],"greatly":[127],"aid":[128],"creation":[131],"high-quality":[133],"data,":[134],"fostering":[135],"advancement":[137],"dialogue":[139],"systems.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}