{"id":"https://openalex.org/W4416852257","doi":"https://doi.org/10.1109/taslpro.2026.3688415","title":"Dopamine Audiobook: A Training-Free MLLM Agent for Emotional and Immersive Audiobook Generation","display_name":"Dopamine Audiobook: A Training-Free MLLM Agent for Emotional and Immersive Audiobook Generation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416852257","doi":"https://doi.org/10.1109/taslpro.2026.3688415"},"language":"en","primary_location":{"id":"doi:10.1109/taslpro.2026.3688415","doi":"https://doi.org/10.1109/taslpro.2026.3688415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslpro.2026.3688415","pdf_url":null,"source":{"id":"https://openalex.org/S5407042752","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"2998-4173","issn":["2998-4173"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-3"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech and Language Processing","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.11002","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080314231","display_name":"Yan Rong","orcid":"https://orcid.org/0009-0006-0857-203X","observed_orcids":["https://orcid.org/0009-0006-0857-203X"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Rong","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-0857-203X","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024093770","display_name":"Shan Yang","orcid":"https://orcid.org/0000-0002-3705-3726","observed_orcids":["https://orcid.org/0000-0002-3705-3726","https://orcid.org/0000-0003-4464-146X"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Yang","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-4464-146X","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023442511","display_name":"Chengyu Li","orcid":"https://orcid.org/0000-0001-6829-0209","observed_orcids":["https://orcid.org/0000-0001-6829-0209","https://orcid.org/0000-0002-6644-5104"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxing Li","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6644-5104","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844","observed_orcids":["https://orcid.org/0000-0003-0520-6844"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0520-6844","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418818","display_name":"Li Liu","orcid":"https://orcid.org/0000-0002-4497-0135","observed_orcids":["https://orcid.org/0000-0002-4497-0135"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4497-0135","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":["https://openalex.org/I4405261251"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01881315,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"2526","last_page":"2538"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9945999979972839,"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":0.9945999979972839,"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/T10860","display_name":"Speech and Audio Processing","score":0.002199999988079071,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.001500000013038516,"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/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9079999923706055},{"id":"https://openalex.org/keywords/emotional-speech-synthesis","display_name":"emotional speech synthesis","score":0.6700000166893005},{"id":"https://openalex.org/keywords/immersive-audio","display_name":"immersive audio","score":0.6340000033378601},{"id":"https://openalex.org/keywords/self-criticism","display_name":"self-criticism","score":0.6990000009536743},{"id":"https://openalex.org/keywords/perspective-taking","display_name":"perspective taking","score":0.6990000009536743},{"id":"https://openalex.org/keywords/human-preference-alignment","display_name":"human preference alignment","score":0.7310000061988831}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.7124999761581421},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6692000031471252},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5419999957084656},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.49570000171661377},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.438400000333786},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33180001378059387},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.3037000000476837},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2578999996185303}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslpro.2026.3688415","doi":"https://doi.org/10.1109/taslpro.2026.3688415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslpro.2026.3688415","pdf_url":null,"source":{"id":"https://openalex.org/S5407042752","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"2998-4173","issn":["2998-4173"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-3"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2504.11002","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.11002","pdf_url":"https://arxiv.org/pdf/2504.11002","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.11002","doi":"https://doi.org/10.48550/arxiv.2504.11002","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.11002","pdf_url":null,"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,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.11002","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.11002","pdf_url":"https://arxiv.org/pdf/2504.11002","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1810916130","display_name":null,"funder_award_id":"2025A15150122 96","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G4221860282","display_name":null,"funder_award_id":"62471420","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5332081803","display_name":null,"funder_award_id":"2023A03J0008","funder_id":"https://openalex.org/F4320323537","funder_display_name":"Hong Kong University of Science and Technology"},{"id":"https://openalex.org/G939200457","display_name":null,"funder_award_id":"62101351","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/F4320323537","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416852257.pdf","grobid_xml":"https://content.openalex.org/works/W4416852257.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Audiobook":[0],"generation":[1,24,111,125],"aims":[2],"to":[3,166],"create":[4],"rich,":[5],"immersive":[6,109],"listening":[7],"experiences":[8],"from":[9],"multimodal":[10,90],"inputs,":[11],"but":[12],"current":[13],"approaches":[14],"face":[15],"three":[16],"critical":[17],"challenges:":[18],"(1)":[19],"the":[20,42,58],"lack":[21],"of":[22,25,60],"synergistic":[23],"diverse":[26,72,123],"audio":[27,103,124,198],"types":[28],"(e.g.,":[29],"speech,":[30],"sound":[31],"effects,":[32],"and":[33,38,56,71,102,108,112,129,144,162,169,195],"music)":[34],"with":[35,66,126,192],"precise":[36],"temporal":[37,130],"semantic":[39,128],"alignment;":[40],"(2)":[41],"difficulty":[43],"in":[44,52],"conveying":[45],"expressive,":[46],"fine-grained":[47],"emotions,":[48],"which":[49],"often":[50],"results":[51,173],"machine-like":[53],"vocal":[54],"outputs;":[55],"(3)":[57],"absence":[59],"automated":[61],"evaluation":[62,157,187],"frameworks":[63],"that":[64,175],"align":[65],"human":[67,193],"preferences":[68,194],"for":[69,105,122,150],"complex":[70],"audio.":[73],"To":[74,132],"address":[75],"these":[76],"issues,":[77],"we":[78,115,135,152],"propose":[79,117],"Dopamine":[80],"Audiobook,":[81],"a":[82,89,118,154],"novel":[83,155],"unified":[84],"training-free":[85],"multi-agent":[86],"system,":[87],"where":[88],"large":[91],"language":[92],"model":[93,147],"(MLLM)":[94],"serves":[95],"two":[96],"specialized":[97],"roles":[98],"(i.e.,":[99],"speech":[100],"designer":[101],"designer)":[104],"emotional,":[106],"human-like,":[107],"audiobook":[110],"evaluation.":[113],"Specifically,":[114],"firstly":[116],"flow-based,":[119],"context-aware":[120],"framework":[121,158,188],"word-level":[127,138],"alignment.":[131],"enhance":[133],"expressiveness,":[134],"then":[136],"design":[137],"paralinguistic":[139],"augmentation,":[140],"utterance-level":[141],"prosody":[142],"retrieval,":[143],"adaptive":[145],"TTS":[146],"selection.":[148],"Finally,":[149],"evaluation,":[151],"introduce":[153],"MLLM-based":[156],"incorporating":[159],"self-critique,":[160],"perspective-taking,":[161],"psychological":[163],"MagicEmo":[164],"prompts":[165],"ensure":[167],"human-aligned":[168],"self-aligned":[170],"assessments.":[171],"Experimental":[172],"demonstrate":[174],"our":[176,186],"method":[177],"achieves":[178],"state-of-the-art":[179],"(SOTA)":[180],"performance":[181],"on":[182],"multiple":[183],"metrics.":[184],"Importantly,":[185],"shows":[189],"better":[190],"alignment":[191],"transferability":[196],"across":[197],"tasks.":[199]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}
