Search Results - "Bak, Taejun"

SYNTHE-SEES: Face Based Text-to-Speech for Virtual Speaker by Park, Jae Hyun, Maeng, Joon-Gyu, Bak, TaeJun, Joo, Young-Sun

“…Recent virtual voice generation researches have limitations in that they results in low-quality voice and generate inconsistent voice from the same speaker's…”
Get full text

MultiVerse: Efficient and Expressive Zero-Shot Multi-Task Text-to-Speech by Bak, Taejun, Eom, Youngsik, Choi, SeungJae, Joo, Young-Sun

“…Text-to-speech (TTS) systems that scale up the amount of training data have achieved significant improvements in zero-shot speech synthesis. However, these…”
Get full text

Avocodo: Generative Adversarial Network for Artifact-free Vocoder by Bak, Taejun, Lee, Junmo, Bae, Hanbin, Yang, Jinhyeok, Bae, Jae-Sung, Joo, Young-Sun

“…Neural vocoders based on the generative adversarial neural network (GAN) have been widely used due to their fast inference speed and lightweight networks while…”
Get full text

GANSpeech: Adversarial Training for High-Fidelity Multi-Speaker Speech Synthesis by Yang, Jinhyeok, Bae, Jae-Sung, Bak, Taejun, Kim, Youngik, Cho, Hoon-Young

“…Recent advances in neural multi-speaker text-to-speech (TTS) models have enabled the generation of reasonably good speech quality with a single model and made…”
Get full text

FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis by Bak, Taejun, Bae, Jae-Sung, Bae, Hanbin, Kim, Young-Ik, Cho, Hoon-Young

“…Methods for modeling and controlling prosody with acoustic features have been proposed for neural text-to-speech (TTS) models. Prosodic speech can be generated…”
Get full text