2 code implementations • 27 Jun 2022 • Taejun Bak, Junmo Lee, Hanbin Bae, Jinhyeok Yang, Jae-Sung Bae, Young-Sun Joo
Therefore, in this paper, we investigate the relationship between these artifacts and GAN-based vocoders and propose a GAN-based vocoder, called Avocodo, that allows the synthesis of high-fidelity speech with reduced artifacts.
no code implementations • 12 Apr 2022 • Hanbin Bae, Young-Sun Joo
To address this issue, we propose two algorithms to improve the robustness of FastPitch.
1 code implementation • 29 Jun 2021 • Taejun Bak, Jae-Sung Bae, Hanbin Bae, Young-Ik Kim, Hoon-Young Cho
Methods for modeling and controlling prosody with acoustic features have been proposed for neural text-to-speech (TTS) models.
no code implementations • 29 Jun 2021 • Gyeong-Hoon Lee, Tae-Woo Kim, Hanbin Bae, Min-Ji Lee, Young-Ik Kim, Hoon-Young Cho
N-Singer consists of a Transformer-based mel-generator, a convolutional network-based postnet, and voicing-aware discriminators.
no code implementations • 4 Mar 2021 • Hanbin Bae, Jae-Sung Bae, Young-Sun Joo, Young-Ik Kim, Hoon-Young Cho
Second, the GST-TTS model with an auxiliary quality classifier is trained with the filtered speech and a small amount of clean speech.