{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:09:38Z","timestamp":1775200178140,"version":"3.50.1"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434744","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["EmoBiMamba-TTS: Bidirectional State Space Model for Emotion-Intensity Controllable Text-to-Speech"],"prefix":"10.1109","author":[{"given":"Insung","family":"Ham","sequence":"first","affiliation":[{"name":"Korea University,Department of Electrical and Electronic Engineering,Seoul,South Korea"}]},{"given":"Bonwha","family":"Ku","sequence":"additional","affiliation":[{"name":"Korea University,Department of Electrical and Electronic Engineering,Seoul,South Korea"}]},{"given":"Hanseok","family":"Ko","sequence":"additional","affiliation":[{"name":"Korea University,Department of Electrical and Electronic Engineering,Seoul,South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.4324\/9780203961278"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1108\/14684521311311667"},{"key":"ref3","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"International Conference on Learning Representations","author":"Ren"},{"key":"ref4","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2301.02111"},{"key":"ref5","article-title":"Naturalspeech: Efficient tts with pre-trained language model","author":"Wang","year":"2023","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref6","article-title":"Styletts2: Multi-speaker style transfer with duration modeling","volume-title":"Proc. Interspeech","author":"Wang"},{"key":"ref7","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proceedings of ICML","author":"Wang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2023-17"},{"key":"ref9","first-page":"1","article-title":"Controllable emotion transfer for end-to-end speech synthesis","volume-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing","author":"Zhou","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-398"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268571"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097118"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3233324"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003829"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095621"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1317"},{"key":"ref17","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","volume-title":"International Conference on Learning Representations","author":"Gu"},{"key":"ref18","article-title":"Can mamba learn how to learn? a comparative study on in-context learning tasks","volume-title":"International Conference on Machine Learning","author":"Park"},{"key":"ref19","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"arXiv preprint arXiv:2401.09417"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-994"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889391"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3566210"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3483009"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","first-page":"1573","article-title":"Emospeech: A multimodal multi-speaker emotional speech synthesis system","volume-title":"Proceedings of Interspeech","author":"Kim"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1238"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-971"},{"key":"ref31","article-title":"Diffgan-tts: High-fidelity and efficient text-tospeech with denoising diffusion gans","author":"Liu","year":"2022","journal-title":"arXiv preprint arXiv:2201.11972"},{"key":"ref32","article-title":"Hungry hungry hippos: Towards language modeling with state space models","volume-title":"Proceedings of the 11th International Conference on Learning Representations (ICLR)","author":"Dao"},{"key":"ref33","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"Proceedings of the 11th International Conference on Learning Representations (ICLR)","author":"Gu"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"ref36","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint arXiv:1607.06450"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-103"},{"key":"ref38","first-page":"93","article-title":"Generative adversarial network based acoustic scene training set augmentation and selection using svm hyper-plane","author":"Mun","year":"2017","journal-title":"DCASE"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2025.110590"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3092735"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref44","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning.","author":"Radford"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434744.pdf?arnumber=11434744","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:16Z","timestamp":1775192356000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434744\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434744","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}