{"id":"https://openalex.org/W4400678062","doi":"https://doi.org/10.1162/tacl_a_00678","title":"Can Authorship Attribution Models Distinguish Speakers in Speech Transcripts?","display_name":"Can Authorship Attribution Models Distinguish Speakers in Speech Transcripts?","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400678062","doi":"https://doi.org/10.1162/tacl_a_00678"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00678","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00678","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00678/2461933/tacl_a_00678.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00678/2461933/tacl_a_00678.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080093830","display_name":"Cristina Aggazzotti","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cristina Aggazzotti","raw_affiliation_strings":["Johns Hopkins University, USA. caggazz1@jhu.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, USA. caggazz1@jhu.edu","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111560316","display_name":"Nicholas Andrews","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas Andrews","raw_affiliation_strings":["Johns Hopkins University, USA. noa@jhu.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, USA. noa@jhu.edu","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104039140","display_name":"Elizabeth A. T. Smith","orcid":null},"institutions":[{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Elizabeth Allyn Smith","raw_affiliation_strings":["Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al, Canada. smith.elizabeth_allyn@uqam.ca"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al, Canada. smith.elizabeth_allyn@uqam.ca","institution_ids":["https://openalex.org/I159129438"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1114,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.80750558,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"12","issue":null,"first_page":"875","last_page":"891"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9998000264167786,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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":0.7951309680938721},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.7217699885368347},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.6993181705474854},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5690808296203613},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5272150039672852},{"id":"https://openalex.org/keywords/attribution","display_name":"Attribution","score":0.5222421884536743},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.4837739169597626},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.481403112411499},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46177351474761963},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4390137195587158},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.43574512004852295},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.43475890159606934},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.42341962456703186},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2642664313316345},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.18872812390327454},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1246042251586914},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.10091736912727356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7951309680938721},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7217699885368347},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.6993181705474854},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5690808296203613},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5272150039672852},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.5222421884536743},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.4837739169597626},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.481403112411499},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46177351474761963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4390137195587158},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.43574512004852295},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.43475890159606934},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.42341962456703186},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2642664313316345},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18872812390327454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1246042251586914},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.10091736912727356},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00678","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00678","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00678/2461933/tacl_a_00678.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8625df207b1b4e56be8c6005c3d6aa97","is_oa":true,"landing_page_url":"https://doaj.org/article/8625df207b1b4e56be8c6005c3d6aa97","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 12 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00678","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00678","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00678/2461933/tacl_a_00678.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400678062.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W140312209","https://openalex.org/W2091612886","https://openalex.org/W2116971293","https://openalex.org/W2139445257","https://openalex.org/W2153890685","https://openalex.org/W2335348029","https://openalex.org/W2759083144","https://openalex.org/W2768253500","https://openalex.org/W2890964092","https://openalex.org/W2953952943","https://openalex.org/W2963579919","https://openalex.org/W2970641574","https://openalex.org/W2972848589","https://openalex.org/W3008918149","https://openalex.org/W3085984954","https://openalex.org/W3092234035","https://openalex.org/W3098557217","https://openalex.org/W3169121689","https://openalex.org/W3197685490","https://openalex.org/W4205619213","https://openalex.org/W4223992738","https://openalex.org/W4300032027","https://openalex.org/W4308174778","https://openalex.org/W4385359140","https://openalex.org/W4389064379","https://openalex.org/W4389518717","https://openalex.org/W6605752562","https://openalex.org/W6633301397","https://openalex.org/W6691615568","https://openalex.org/W6890254401","https://openalex.org/W7014295595"],"related_works":["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/W2380599343","https://openalex.org/W2181793145","https://openalex.org/W3163320880","https://openalex.org/W2365703075"],"abstract_inverted_index":{"Abstract":[0],"Authorship":[1],"verification":[2,121],"is":[3,18,44,167],"the":[4,14,22,32,61,116,128,131,174,184],"task":[5],"of":[6,24,34,82,103,123,130,141,173,176,186],"determining":[7],"if":[8],"two":[9],"distinct":[10],"writing":[11],"samples":[12],"share":[13],"same":[15,117],"author":[16],"and":[17,52,73,112,143],"typically":[19],"concerned":[20],"with":[21,105],"attribution":[23,33,92,151],"written":[25,149],"text.":[26],"In":[27],"this":[28,58,134],"paper,":[29],"we":[30,107],"explore":[31],"transcribed":[35,64],"speech,":[36],"which":[37,78],"poses":[38],"novel":[39],"challenges.":[40],"The":[41],"main":[42],"challenge":[43],"that":[45,147],"many":[46],"stylistic":[47],"features,":[48],"such":[49,69],"as":[50,70,164,181,183],"punctuation":[51],"capitalization,":[53],"are":[54],"not":[55],"informative":[56],"in":[57,115,157],"setting.":[59],"On":[60],"other":[62,67],"hand,":[63],"speech":[65,97,189],"exhibits":[66],"patterns,":[68],"filler":[71],"words":[72],"backchannels":[74],"(e.g.,":[75],"um,":[76],"uh-huh),":[77],"may":[79],"be":[80],"characteristic":[81],"different":[83],"speakers.":[84],"We":[85,126,170],"propose":[86],"a":[87,139],"new":[88,135],"benchmark":[89,136],"for":[90],"speaker":[91],"focused":[93],"on":[94,133,179,188],"human-transcribed":[95],"conversational":[96,165],"transcripts.":[98],"To":[99],"limit":[100],"spurious":[101],"associations":[102],"speakers":[104,113],"topic,":[106],"employ":[108],"both":[109],"conversation":[110,118],"prompts":[111],"participating":[114],"to":[119,191],"construct":[120],"trials":[122],"varying":[124],"difficulties.":[125],"establish":[127],"state":[129],"art":[132],"by":[137],"comparing":[138],"suite":[140],"neural":[142],"non-neural":[144],"baselines,":[145],"finding":[146],"although":[148],"text":[150],"models":[152],"achieve":[153],"surprisingly":[154],"good":[155],"performance":[156,180],"certain":[158],"settings,":[159],"they":[160],"perform":[161],"markedly":[162],"worse":[163],"topic":[166],"increasingly":[168],"controlled.":[169],"present":[171],"analyses":[172],"impact":[175],"transcription":[177],"style":[178],"well":[182],"ability":[185],"fine-tuning":[187],"transcripts":[190],"improve":[192],"performance.1":[193]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}