{"id":"https://openalex.org/W4224926192","doi":"https://doi.org/10.1109/icassp43922.2022.9747098","title":"EMOQ-TTS: Emotion Intensity Quantization for Fine-Grained Controllable Emotional Text-to-Speech","display_name":"EMOQ-TTS: Emotion Intensity Quantization for Fine-Grained Controllable Emotional Text-to-Speech","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224926192","doi":"https://doi.org/10.1109/icassp43922.2022.9747098"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747098","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5070915840","display_name":"Chae-Bin Im","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Chae-Bin Im","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Korea","Department of Artificial Intelligence, Korea University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320186","display_name":"Sang-Hoon Lee","orcid":"https://orcid.org/0000-0002-1477-6569"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sang-Hoon Lee","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Korea","Korea University,Department of Brain and Cognitive Engineering,Seoul,Korea","Department of Brain and Cognitive Engineering, Korea University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Korea University,Department of Brain and Cognitive Engineering,Seoul,Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Brain and Cognitive Engineering, Korea University, Seoul, Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007493723","display_name":"Seung-Bin Kim","orcid":"https://orcid.org/0000-0002-2287-9111"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seung-Bin Kim","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Korea","Department of Artificial Intelligence, Korea University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011014617","display_name":"Seong\u2010Whan Lee","orcid":"https://orcid.org/0000-0002-6249-4996"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seong-Whan Lee","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Korea","Korea University,Department of Brain and Cognitive Engineering,Seoul,Korea","Department of Brain and Cognitive Engineering, Korea University, Seoul, Korea","Department of Artificial Intelligence, Korea University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Korea University,Department of Brain and Cognitive Engineering,Seoul,Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Brain and Cognitive Engineering, Korea University, Seoul, Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5070915840"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":4.2663,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.95507192,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6317","last_page":"6321"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9977999925613403,"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/T11309","display_name":"Music and Audio Processing","score":0.9950000047683716,"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/utterance","display_name":"Utterance","score":0.7687584161758423},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6478400230407715},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6466147303581238},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.6022135019302368},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5393945574760437},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4957829415798187},{"id":"https://openalex.org/keywords/emotional-expression","display_name":"Emotional expression","score":0.4813557267189026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3273398280143738},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2653685212135315},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.25136083364486694},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11375740170478821},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.069180428981781}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7687584161758423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6478400230407715},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6466147303581238},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.6022135019302368},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5393945574760437},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4957829415798187},{"id":"https://openalex.org/C143110190","wikidata":"https://www.wikidata.org/wiki/Q5373787","display_name":"Emotional expression","level":2,"score":0.4813557267189026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3273398280143738},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2653685212135315},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.25136083364486694},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11375740170478821},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.069180428981781},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747098","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.49000000953674316,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321373","display_name":"Korea University","ror":"https://ror.org/047dqcg40"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W31986064","https://openalex.org/W116902681","https://openalex.org/W232876404","https://openalex.org/W1882958252","https://openalex.org/W1973207880","https://openalex.org/W1975163393","https://openalex.org/W2039240409","https://openalex.org/W2089468765","https://openalex.org/W2102003408","https://openalex.org/W2102148524","https://openalex.org/W2107860279","https://openalex.org/W2294130536","https://openalex.org/W2473461482","https://openalex.org/W2770743791","https://openalex.org/W2794490148","https://openalex.org/W2885800352","https://openalex.org/W2963609956","https://openalex.org/W3015841875","https://openalex.org/W3033411150","https://openalex.org/W3034949308","https://openalex.org/W3126404598","https://openalex.org/W3135644023","https://openalex.org/W3146550708","https://openalex.org/W3150572638","https://openalex.org/W3162387328","https://openalex.org/W3174285493","https://openalex.org/W3174758275","https://openalex.org/W3196468212","https://openalex.org/W3198843334","https://openalex.org/W3201011692","https://openalex.org/W4385245566","https://openalex.org/W6604828220","https://openalex.org/W6609126827","https://openalex.org/W6639480849","https://openalex.org/W6720691856","https://openalex.org/W6739901393","https://openalex.org/W6746238782","https://openalex.org/W6750489868","https://openalex.org/W6778823374","https://openalex.org/W6790138166","https://openalex.org/W6796730497","https://openalex.org/W6801572894"],"related_works":["https://openalex.org/W2036697162","https://openalex.org/W2140812588","https://openalex.org/W2411113819","https://openalex.org/W2072887367","https://openalex.org/W2332386680","https://openalex.org/W2561315646","https://openalex.org/W2248621902","https://openalex.org/W2003779889","https://openalex.org/W2164760767","https://openalex.org/W4205698120"],"abstract_inverted_index":{"Although":[0],"recent":[1],"advances":[2],"in":[3,37,105],"text-to-speech":[4],"(TTS)":[5],"have":[6],"shown":[7],"significant":[8],"improvement,":[9],"it":[10],"is":[11,73],"still":[12],"limited":[13],"to":[14,42],"emotional":[15,20,39,56,87,106],"speech":[16,57,91],"synthesis.":[17],"To":[18],"produce":[19],"speech,":[21],"most":[22],"works":[23],"utilize":[24],"emotion":[25,29,45,61,65,71],"information":[26,62,72],"extracted":[27],"from":[28],"labels":[30,95],"or":[31],"reference":[32],"audio.":[33],"However,":[34],"they":[35],"result":[36],"monotonous":[38],"expression":[40,88],"due":[41],"the":[43,68,86,101],"utterance-level":[44],"conditions.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50],"propose":[51],"EmoQ-TTS,":[52],"which":[53],"synthesizes":[54],"expressive":[55],"by":[58,75,92],"conditioning":[59,93],"phoneme-wise":[60],"with":[63],"fine-grained":[64],"intensity.":[66],"Here,":[67],"intensity":[69,77,94],"of":[70,89,103],"rendered":[74],"distance-based":[76],"quantization":[78],"without":[79],"human":[80],"labeling.":[81],"We":[82],"can":[83],"also":[84],"control":[85],"synthesized":[90],"manually.":[96],"The":[97],"experimental":[98],"results":[99],"demonstrate":[100],"superiority":[102],"EmoQ-TTS":[104],"expressiveness":[107],"and":[108],"controllability.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}