{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:33:24Z","timestamp":1763192004522,"version":"3.45.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11229144","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Fine-grained Voice Customization via Intensity Guided Latent Space Exploration"],"prefix":"10.1109","author":[{"given":"Kwan-yeung","family":"Wong","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University,Department of Data Science & Artificial Intelligence,Hong Kong,China"}]},{"given":"Fu-lai","family":"Chung","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University,Department of Data Science & Artificial Intelligence,Hong Kong,China"}]}],"member":"263","reference":[{"article-title":"Review of end-to-end speech synthesis technology based on deep learning","year":"2021","author":"Mu","key":"ref1"},{"key":"ref2","first-page":"79","article-title":"Text-to-speech technology in human-computer interaction","volume-title":"5th conference on human computer interaction in Southern Africa, South Africa (CHISA 2006, ACM SIGHI)","author":"Mohasi"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1639642.1639704"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.682"},{"key":"ref5","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume":"31","author":"Jia","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref6","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"International conference on machine learning","author":"Wang"},{"key":"ref7","article-title":"Neural voice cloning with a few samples","volume":"31","author":"Arik","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1093\/iwc\/iwz016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3386867"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3359325"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-589"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10855"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747345"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892169"},{"article-title":"Prompttts 2: Describing and generating voices with text prompt","year":"2023","author":"Leng","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448173"},{"article-title":"Enhancing zero-shot text-to-speech synthesis with human feedback","year":"2024","author":"Chen","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2904"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3233324"},{"key":"ref21","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","volume":"30","author":"Gibiansky","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Wavenet: A generative model for raw audio","volume":"12","author":"Den Oord","year":"2016"},{"key":"ref23","first-page":"2709","article-title":"Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone","volume-title":"International Conference on Machine Learning","author":"Casanova"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.17762\/jaz.v44iS7.2721"},{"key":"ref25","first-page":"10659","article-title":"Gibbs sampling with people","volume":"33","author":"Harrison","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780199982295.013.29"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2020.02.001"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126281"},{"article-title":"Speakernet: 1d depth-wise separable convolutional network for text-independent speaker recognition and verification","year":"2020","author":"Koluguri","key":"ref30"},{"article-title":"Auto-encoding variational bayes","year":"2013","author":"Kingma","key":"ref31"},{"article-title":"Common voice: A massively-multilingual speech corpus","year":"2019","author":"Ardila","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3304724"},{"key":"ref34","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2382"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"issue":"11","key":"ref37","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11229144.pdf?arnumber=11229144","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:30:06Z","timestamp":1763191806000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11229144\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11229144","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}