{"id":"https://openalex.org/W7160207615","doi":"https://doi.org/10.63317/4d596vd4x2xr","title":"Beyond Transcripts: Iterative Peer-Editing with Audio Unlocks High-Quality Human Summaries of Conversational Speech","display_name":"Beyond Transcripts: Iterative Peer-Editing with Audio Unlocks High-Quality Human Summaries of Conversational Speech","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W7160207615","doi":"https://doi.org/10.63317/4d596vd4x2xr"},"language":null,"primary_location":{"id":"doi:10.63317/4d596vd4x2xr","is_oa":false,"landing_page_url":"https://doi.org/10.63317/4d596vd4x2xr","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2605.17652","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5095094640","display_name":"Kaavya Chaparala","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaavya Chaparala","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040324682","display_name":"Thomas Thebaud","orcid":"https://orcid.org/0000-0001-8953-7872"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Thebaud","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132807342","display_name":"Jesus Villalba Lopez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jesus Villalba Lopez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135237033","display_name":"Laureano Moro-Velazquez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laureano Moro-Velazquez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041825272","display_name":"Peter Viechnicki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Viechnicki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135144860","display_name":"Najim Dehak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":0.44658188,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6838","last_page":"6855"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.3118000030517578,"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":0.3118000030517578,"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":0.11919999867677689,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.11289999634027481,"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/conversation","display_name":"Conversation","score":0.3379000127315521},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.3111000061035156},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.31060001254081726},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3009999990463257},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.2962000072002411},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2888999879360199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6414999961853027},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4828000068664551},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45890000462532043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4041000008583069},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3151000142097473},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.26510000228881836},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.63317/4d596vd4x2xr","is_oa":false,"landing_page_url":"https://doi.org/10.63317/4d596vd4x2xr","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2605.17652","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.17652","pdf_url":"https://arxiv.org/pdf/2605.17652","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,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2605.17652","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.17652","pdf_url":"https://arxiv.org/pdf/2605.17652","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,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7614496350288391}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7160207615.pdf","grobid_xml":"https://content.openalex.org/works/W7160207615.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"There":[0],"are":[1,100,113,174],"not":[2],"enough":[3],"established":[4],"benchmarks":[5,14,90,156],"for":[6,152],"the":[7,41,71,74,84,153],"task":[8],"fo":[9],"speech":[10],"summarization.":[11],"Creating":[12],"new":[13],"demands":[15],"human":[16,55,62,66,85,150],"annotation,":[17],"as":[18,135,137],"LLMs":[19],"could":[20],"embed":[21],"systemic":[22],"errors":[23],"and":[24,40,116,141,161],"bias":[25],"into":[26],"datasets.":[27],"We":[28,60,81,108],"test":[29],"ten":[30],"annotation":[31],"workflows":[32],"varying":[33],"input":[34],"modality":[35],"(audio,":[36],"transcript,":[37],"or":[38,46],"both)":[39],"inclusion":[42],"of":[43,73,155],"editing":[44],"(self":[45],"peer-editing)":[47],"to":[48,57,65,69,95,133],"investigate":[49],"potential":[50],"quality":[51],"tradeoffs":[52],"from":[53],"using":[54],"annotators":[56,151],"summarize":[58],"audio.":[59],"compare":[61,83],"audio-based":[63,111,131],"summaries":[64,68,99,112,132],"transcript-based":[67],"track":[70],"impact":[72],"different":[75],"information":[76],"modalities":[77],"on":[78],"summary":[79],"quality.":[80],"also":[82],"outputs":[86],"against":[87],"four":[88],"LLM":[89,142],"(three":[91],"text,":[92],"one":[93],"audio)":[94],"examine":[96],"whether":[97],"human-written":[98],"less":[101,114],"informative":[102,115,136],"than":[103,119],"highly":[104],"fluent":[105],"automated":[106],"outputs.":[107],"find":[109],"that":[110],"more":[117],"compressed":[118],"transcript":[120,139],"summaries.":[121,143],"However,":[122],"iterative":[123,147],"peer-editing":[124,148],"with":[125],"audio":[126],"mitigates":[127],"this":[128],"difference,":[129],"enabling":[130],"be":[134],"their":[138],"counterparts":[140],"These":[144],"findings":[145],"validate":[146],"among":[149],"creation":[154],"informed":[157],"by":[158],"both":[159],"lexical":[160],"prosodic":[162],"information.":[163],"This":[164],"enables":[165],"crucial":[166],"dataset":[167],"collection":[168],"even":[169],"in":[170],"setting":[171],"where":[172],"transcripts":[173],"unavailable.":[175]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-05-05T00:00:00"}