{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T05:41:06Z","timestamp":1764222066081,"version":"3.46.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/sped67700.2025.11253714","type":"proceedings-article","created":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T19:00:27Z","timestamp":1764183627000},"page":"86-91","source":"Crossref","is-referenced-by-count":0,"title":["Adding Emotion Conditioning in Speech Synthesis via Multi-Term Classifier-Free Guidance"],"prefix":"10.1109","author":[{"given":"Radu-George","family":"Bolborici","sequence":"first","affiliation":[{"name":"National University of Science and Technology Politehnica,Bucharest,Romania"}]},{"given":"Ana","family":"Neac\u015fu","sequence":"additional","affiliation":[{"name":"National University of Science and Technology Politehnica,Bucharest,Romania"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.313"},{"key":"ref2","article-title":"Better speech synthesis through scaling","author":"Betker","year":"2023","journal-title":"arXiv preprint arXiv:2305.07243"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-398"},{"volume-title":"An Approach to Environmental Psychology","year":"1974","author":"Mehrabian","key":"ref5"},{"key":"ref6","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv preprint arXiv:2006.04558"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.466"},{"volume-title":"Metavoice-1b","year":"2025","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref11","article-title":"Vocos: Closing the gap between time-domain and fourier-based neural vocoders for high-quality audio synthesis","author":"Siuzdak","year":"2023","journal-title":"arXiv preprint arXiv:2306.00814"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref14","article-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","author":"Du","year":"2024","journal-title":"arXiv preprint arXiv:2407.05407"},{"key":"ref15","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings","author":"Glorot"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref17","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint arXiv:2207.12598"},{"key":"ref19","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832315"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1774"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/s21227665"}],"event":{"name":"2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","start":{"date-parts":[[2025,10,19]]},"location":"Cluj-Napoca, Romania","end":{"date-parts":[[2025,10,22]]}},"container-title":["2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11251505\/11251597\/11253714.pdf?arnumber=11253714","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T05:37:51Z","timestamp":1764221871000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11253714\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/sped67700.2025.11253714","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}