{"id":"https://openalex.org/W4416799850","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248982","title":"Emotional Text-To-Speech Based on Mutual-Information-Guided Emotion-Timbre Disentanglement","display_name":"Emotional Text-To-Speech Based on Mutual-Information-Guided Emotion-Timbre Disentanglement","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799850","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248982"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11248982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5007632597","display_name":"Yang Jianing","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jianing Yang","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["Institute of Science Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103015161","display_name":"Takahiro Shinozaki","orcid":"https://orcid.org/0000-0001-8114-8450"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takahiro Shinozaki","raw_affiliation_strings":["Institute of Science Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083394213","display_name":"Yuki Saito","orcid":"https://orcid.org/0000-0002-7967-2613"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Saito","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5007632597"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41264467,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"567","last_page":"572"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.8440999984741211,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.8440999984741211,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.041600000113248825,"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":0.02710000053048134,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.6726999878883362},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5662999749183655},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.4603999853134155},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44429999589920044},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4339999854564667},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4260999858379364},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.3939000070095062},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.37619999051094055}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.6726999878883362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6067000031471252},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5662999749183655},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.476500004529953},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.4603999853134155},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44429999589920044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4341000020503998},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4339999854564667},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4260999858379364},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3573000133037567},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33649998903274536},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2944999933242798},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C96851999","wikidata":"https://www.wikidata.org/wiki/Q848369","display_name":"Subconscious","level":3,"score":0.2870999872684479},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.27559998631477356},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2578999996185303},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11248982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2519091744","https://openalex.org/W2963417023","https://openalex.org/W2964243274","https://openalex.org/W3015212100","https://openalex.org/W3135547455","https://openalex.org/W3198609073","https://openalex.org/W3215615641","https://openalex.org/W4205742757","https://openalex.org/W4225303561","https://openalex.org/W4243316134","https://openalex.org/W4319300748","https://openalex.org/W4385822268"],"related_works":[],"abstract_inverted_index":{"Current":[0],"emotional":[1,37,120],"Text-To-Speech":[2],"(TTS)":[3],"and":[4,73,76,99,110,117],"style":[5,15,60,80],"transfer":[6],"methods":[7],"rely":[8],"on":[9],"reference":[10,28,53,84],"encoders":[11],"to":[12,63],"control":[13],"global":[14],"or":[16],"emotion":[17,44,74],"vectors,":[18],"but":[19],"do":[20],"not":[21],"capture":[22],"nuanced":[23],"acoustic":[24],"details":[25],"of":[26,51,108,119],"the":[27,52,83,106,115],"speech.":[29,54,85,102],"To":[30],"this":[31],"end,":[32],"we":[33],"propose":[34],"a":[35,59],"novel":[36],"TTS":[38,94,121],"method":[39,57,62,91],"that":[40,89],"enables":[41],"fine-grained":[42,111],"phoneme-level":[43],"embedding":[45],"prediction":[46],"while":[47],"disentangling":[48],"intrinsic":[49],"attributes":[50],"The":[55],"proposed":[56],"employs":[58],"disentanglement":[61],"guide":[64],"two":[65],"feature":[66],"extractors,":[67],"reducing":[68],"mutual":[69],"information":[70],"between":[71],"timbre":[72],"features,":[75],"effectively":[77],"separating":[78],"distinct":[79],"components":[81],"from":[82],"Experimental":[86],"results":[87],"demonstrate":[88],"our":[90],"outperforms":[92],"baseline":[93],"systems":[95],"in":[96,113],"generating":[97],"natural":[98],"emotionally":[100],"rich":[101],"This":[103],"work":[104],"highlights":[105],"potential":[107],"disentangled":[109],"representations":[112],"advancing":[114],"quality":[116],"flexibility":[118],"systems.":[122],"<sup":[123],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[124,126],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[125],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>The":[127],"synthesized":[128],"audio":[129],"samples":[130],"are":[131],"available":[132],"at":[133],"https://baleyang.github.io/emotion-timbre-disentangled-tts/":[134]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}