{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:22:51Z","timestamp":1775229771667,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T00:00:00Z","timestamp":1728172800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T00:00:00Z","timestamp":1728172800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,6]]},"DOI":"10.1109\/smc54092.2024.10831218","type":"proceedings-article","created":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:39:20Z","timestamp":1737398360000},"page":"1151-1156","source":"Crossref","is-referenced-by-count":1,"title":["PromotiCon: Prompt-based Emotion Controllable Text-to-Speech via Prompt Generation and Matching"],"prefix":"10.1109","author":[{"given":"Ji\u2013Eun","family":"Lee","sequence":"first","affiliation":[{"name":"Korea University, Anam-dong,Department of Artificial Intelligence,Seongbukku,Seoul,Korea,02841"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seung\u2013Bin","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University, Anam-dong,Department of Artificial Intelligence,Seongbukku,Seoul,Korea,02841"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deok\u2013Hyeon","family":"Cho","sequence":"additional","affiliation":[{"name":"Korea University, Anam-dong,Department of Artificial Intelligence,Seongbukku,Seoul,Korea,02841"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seong\u2013Whan","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea University, Anam-dong,Department of Artificial Intelligence,Seongbukku,Seoul,Korea,02841"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"FastSpeech 2: Fast and High-Quality End-to- End Text to Speech","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Ren","year":"2020"},{"key":"ref2","article-title":"HierSpeech: Bridging the Gap between Text and Speech by Hierarchical Variational Inference using Self-supervised Representations for Speech Synthesis","author":"Lee","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref3","article-title":"Conditional Variational Au-toencoder with Adversarial Learning for End-to-End Text-to-Speech","volume-title":"Int. Conf. Mach. Learn. (ICML)","author":"Kim","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbe.2019.12.002"},{"key":"ref5","article-title":"Deep Reinforcement Learning in Continuous Action Spaces: a Case Study in the Game of Simulated Curling","volume-title":"Int. Conf. Mach. Learn. (ICML)","author":"Lee","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3006907"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/brainsci9120348"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC44109.2020.9175874"},{"key":"ref9","article-title":"Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis","volume-title":"Int. Conf. Mach. Learn. (ICML)","author":"Wang","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-754"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3395994"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383524"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683623"},{"key":"ref14","article-title":"AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss","volume-title":"Int. Conf. Mach. Learn. (ICML)","author":"Qian","year":"2019"},{"key":"ref15","article-title":"GPT-4 Technical Report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Visual Instruction Tuning","author":"Liu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1779"},{"key":"ref19","article-title":"PromptTTS 2: Describing and Generating Voices with Text Prompt","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Leng","year":"2023"},{"key":"ref20","article-title":"PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-to-Speech using Natural Language Descriptions","volume-title":"IEEE Int. Conf. Acoust. Speech Signal Process. (ICASSP)","author":"Reo","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3402088"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747098"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-251"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268571"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145297"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095619"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095776"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3164181"},{"key":"ref29","first-page":"1","article-title":"Domain-Adversarial Training of Neural Networks","volume":"17","author":"Ganin","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref30","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume-title":"Conf. North Am. Chapt. Assoc. Comput. Linguist. (NAACL)","author":"Devlin","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref32","first-page":"1","article-title":"Linear Discriminant Analysis-A Brief Tutorial","volume":"18","author":"Balakrishnama","year":"1998","journal-title":"Inst. Signal Info. Process."},{"key":"ref33","article-title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Lee","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054556"},{"key":"ref35","article-title":"Categorical Reparameterization with Gumbel-Softmax","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Jang","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref38","article-title":"Meta-StyleSpeech: Multi-Speaker Adaptive Text-to-Speech Generation","volume-title":"Int. Conf. Mach. Learn. (ICML)","author":"Min","year":"2021"}],"event":{"name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Kuching, Malaysia","start":{"date-parts":[[2024,10,6]]},"end":{"date-parts":[[2024,10,10]]}},"container-title":["2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830919\/10830920\/10831218.pdf?arnumber=10831218","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T06:31:52Z","timestamp":1737441112000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10831218\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/smc54092.2024.10831218","relation":{},"subject":[],"published":{"date-parts":[[2024,10,6]]}}}