(Reference) Hyeong-Seok, Choi., Juheon, Lee., Wan-Soo, Kim., Jie, Hwan, Lee., Hoon, Heo., Kyogu, Lee. (2021). Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations.. arXiv: Soundhttps://proceedings.neurips.cc/paper_files/paper/2021/file/87682805257e619d49b8e0dfdc14affa-Paper.pdf 이 논문에서는 neural analysis and synthesis(NANSY)라는, 사람 음성 신호의 voice, pitch, speed을 조절..