Masaya Kawamura, Yuma Shirahata, Ryuichi Yamamoto, Kentaro Tachibana. Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform. In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023. pages 1-5, IEEE, 2023. [doi]
@inproceedings{KawamuraSYT23, title = {Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform}, author = {Masaya Kawamura and Yuma Shirahata and Ryuichi Yamamoto and Kentaro Tachibana}, year = {2023}, doi = {10.1109/ICASSP49357.2023.10095296}, url = {https://doi.org/10.1109/ICASSP49357.2023.10095296}, researchr = {https://researchr.org/publication/KawamuraSYT23}, cites = {0}, citedby = {0}, pages = {1-5}, booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023}, publisher = {IEEE}, isbn = {978-1-7281-6327-7}, }