3 papers
cs.SD2025
Sidon: Fast and Robust Open-Source Multilingual Speech Restoration for Large-scale Dataset Cleansing
Wataru Nakata, Yuki Saito, Yota Ueda +1
Large-scale text-to-speech (TTS) systems are limited by the scarcity of clean, multilingual recordings. We introduce Sidon, a fast, open-source speech restoration model that conver…
cs.HC2023
HumanDiffusion: diffusion model using perceptual gradients
Yota Ueda, Shinnosuke Takamichi, Yuki Saito +2
We propose {\it HumanDiffusion,} a diffusion model trained from humans' perceptual gradients to learn an acceptable range of data for humans (i.e., human-acceptable distribution).…
cs.HC2021
HumanACGAN: conditional generative adversarial network with human-based auxiliary classifier and its evaluation in phoneme perception
Yota Ueda, Kazuki Fujii, Yuki Saito +3
We propose a conditional generative adversarial network (GAN) incorporating humans' perceptual evaluations. A deep neural network (DNN)-based generator of a GAN can represent a rea…