{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:37:36Z","timestamp":1771468656474,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002642","name":"Korea University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002642","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747098","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6317-6321","source":"Crossref","is-referenced-by-count":38,"title":["EMOQ-TTS: Emotion Intensity Quantization for Fine-Grained Controllable Emotional Text-to-Speech"],"prefix":"10.1109","author":[{"given":"Chae-Bin","family":"Im","sequence":"first","affiliation":[{"name":"Korea University,Department of Artificial Intelligence,Seoul,Korea"}]},{"given":"Sang-Hoon","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea University,Department of Brain and Cognitive Engineering,Seoul,Korea"}]},{"given":"Seung-Bin","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University,Department of Artificial Intelligence,Seoul,Korea"}]},{"given":"Seong-Whan","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea University,Department of Artificial Intelligence,Seoul,Korea"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/0169-7439(87)80084-9"},{"key":"ref31","first-page":"359","article-title":"Using Dynamic Time Warping to Find Patterns in Time Series","author":"berndt","year":"1994","journal-title":"KDD Workshop"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413876"},{"key":"ref10","article-title":"Expressive Neural Voice Cloning","author":"neekhara","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362069"},{"key":"ref12","article-title":"Controllable Cross-Speaker Emotion Transfer for End-to-End Speech Synthesis","author":"li","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053732"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-377"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383524"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126281"},{"key":"ref17","article-title":"Fastspeech 2: Fast and High-quality End-to-End Text to Speech","author":"ren","year":"2021","journal-title":"Proc International Conference on Learning Representations (ICLR)"},{"key":"ref18","first-page":"6588","article-title":"Fastpitch: Parallel Text-to-Speech with Pitch Prediction","author":"la?cucki","year":"2021","journal-title":"Proc IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3354\/cr030079"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref4","article-title":"A Survey on Neural Speech Synthesis","author":"tan","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-845"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-831"},{"key":"ref6","article-title":"Attention Is All You Need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5194\/gmd-7-1247-2014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref7","first-page":"5180","article-title":"Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis","author":"wang","year":"2018","journal-title":"Proc International Conference on Machine Learning (ICML)"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v35i14.17559","article-title":"Multi-SpectroGAN: High-Diversity and High-Fidelity Spectrogram Generation with Adversarial Style Combination for Speech Synthesis","author":"lee","year":"2021","journal-title":"Proc the AAAI Conference on Artificial Intelligence"},{"key":"ref9","article-title":"Emotional End-to-End Neural Speech Synthesizer","author":"lee","year":"2017"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards End-to-end Speech Synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref20","first-page":"1180","article-title":"Unsupervised Domain Adaptation by Backpropagation","author":"ganin","year":"2015","journal-title":"Proc International Conference on Machine Learning (ICML)"},{"key":"ref22","first-page":"1","article-title":"Linear Discriminant Analysis-a Brief Tutorial","author":"balakrishnama","year":"1998","journal-title":"Institute for signal and information processing"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.930649"},{"key":"ref24","article-title":"Korean Emotional Speech Dataset","year":"2019"},{"key":"ref23","first-page":"82","article-title":"A Review of Statistical Outlier Methods","author":"walfish","year":"2006","journal-title":"Pharmaceutical Technology"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0446-1"},{"key":"ref25","article-title":"EmotionTTS-open-DB Dataset","year":"2019"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747098.pdf?arnumber=9747098","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T03:22:25Z","timestamp":1727061745000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747098\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747098","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}