{"id":"https://openalex.org/W4412888749","doi":"https://doi.org/10.18653/v1/2025.findings-acl.101","title":"Chain-Talker: Chain Understanding and Rendering for Empathetic Conversational Speech Synthesis","display_name":"Chain-Talker: Chain Understanding and Rendering for Empathetic Conversational Speech Synthesis","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888749","doi":"https://doi.org/10.18653/v1/2025.findings-acl.101"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.101","pdf_url":"https://aclanthology.org/2025.findings-acl.101.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.101.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100708728","display_name":"Yifan Hu","orcid":"https://orcid.org/0009-0008-2276-1456"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082746577","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0003-4524-7413"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101499461","display_name":"Yi Ren","orcid":"https://orcid.org/0000-0001-9360-8653"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Ren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101874107","display_name":"Xiang Yin","orcid":"https://orcid.org/0000-0003-0741-4831"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haizhou Li","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":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1988","last_page":"2003"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9415000081062317,"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":0.9415000081062317,"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":0.6805338859558105},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.6275429725646973},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43787938356399536},{"id":"https://openalex.org/keywords/chain","display_name":"Chain (unit)","score":0.4280337691307068},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32479462027549744},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21975991129875183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6805338859558105},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.6275429725646973},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43787938356399536},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.4280337691307068},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32479462027549744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21975991129875183},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.101","pdf_url":"https://aclanthology.org/2025.findings-acl.101.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.101","pdf_url":"https://aclanthology.org/2025.findings-acl.101.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G600008135","display_name":null,"funder_award_id":"62206136","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335581","display_name":"Young Scientists Fund","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888749.pdf","grobid_xml":"https://content.openalex.org/works/W4412888749.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Conversational":[0],"Speech":[1],"Synthesis":[2],"(CSS)":[3],"aims":[4],"to":[5,18,28,114],"align":[6],"synthesized":[7],"speech":[8,35,73,92,107],"with":[9,111],"the":[10,38],"emotional":[11,30],"and":[12,32,68,105,119],"stylistic":[13],"context":[14],"of":[15],"user-agent":[16],"interactions":[17],"achieve":[19],"empathy.Current":[20],"generative":[21],"CSS":[22],"models":[23],"face":[24],"interpretability":[25],"limitations":[26],"due":[27],"insufficient":[29],"perception":[31],"redundant":[33],"discrete":[34],"coding.To":[36],"address":[37],"above":[39],"issues,":[40],"we":[41,81],"present":[42],"Chain-Talker,":[43],"a":[44],"three-stage":[45],"framework":[46],"mimicking":[47],"human":[48],"cognition:":[49],"Emotion":[50],"Understanding":[51,60],"derives":[52],"context-aware":[53],"emotion":[54,79,93,116],"descriptors":[55],"from":[56],"dialogue":[57],"history;":[58],"Semantic":[59],"generates":[61],"compact":[62],"semantic":[63],"codes":[64],"via":[65],"serialized":[66],"prediction;":[67],"Empathetic":[69],"Rendering":[70],"synthesizes":[71],"expressive":[72,104],"by":[74],"integrating":[75],"both":[76],"components.To":[77],"support":[78],"modeling,":[80],"develop":[82],"CSS-EmCap,":[83],"an":[84],"LLM-driven":[85],"automated":[86],"pipeline":[87],"for":[88],"generating":[89],"precise":[90],"conversational":[91],"captions.Experiments":[94],"on":[95],"three":[96],"benchmark":[97],"datasets":[98],"demonstrate":[99],"that":[100],"Chain-Talker":[101],"produces":[102],"more":[103],"empathetic":[106],"than":[108],"existing":[109],"methods,":[110],"CSS-EmCap":[112],"contributing":[113],"reliable":[115],"modeling.The":[117],"code":[118],"demos":[120],"are":[121],"available":[122],"at:":[123],"https://github.com/AI":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}