2 code implementations • 24 Feb 2023 • Junhyeok Lee, Wonbin Jung, Hyunjae Cho, Jaeyeon Kim, Jaehwan Kim
Previous pitch-controllable text-to-speech (TTS) models rely on directly modeling fundamental frequency, leading to low variance in synthesized speech.
2 code implementations • 8 Nov 2022 • Junhyeok Lee, Seungu Han, Hyunjae Cho, Wonbin Jung
Previous generative adversarial network (GAN)-based neural vocoders are trained to reconstruct the exact ground truth waveform from the paired mel-spectrogram and do not consider the one-to-many relationship of speech synthesis.
no code implementations • 24 Jun 2022 • Hyunjae Cho, Wonbin Jung, Junhyeok Lee, Sang Hoon Woo
By the difficulty of obtaining multilingual corpus for given speaker, training multilingual TTS model with monolingual corpora is unavoidable.