Shun Lei, Yixuan Zhou, Liyang Chen, Zhiyong Wu 0001, Xixin Wu, Shiyin Kang, Helen Meng. MSStyleTTS: Multi-Scale Style Modeling With Hierarchical Context Information for Expressive Speech Synthesis. IEEE Transactions on Audio, Speech & Language Processing, 31:3290-3303, 2023. [doi]
@article{LeiZCWWKM23, title = {MSStyleTTS: Multi-Scale Style Modeling With Hierarchical Context Information for Expressive Speech Synthesis}, author = {Shun Lei and Yixuan Zhou and Liyang Chen and Zhiyong Wu 0001 and Xixin Wu and Shiyin Kang and Helen Meng}, year = {2023}, doi = {10.1109/TASLP.2023.3301217}, url = {https://doi.org/10.1109/TASLP.2023.3301217}, researchr = {https://researchr.org/publication/LeiZCWWKM23}, cites = {0}, citedby = {0}, journal = {IEEE Transactions on Audio, Speech & Language Processing}, volume = {31}, pages = {3290-3303}, }