PITS: Variational Pitch Inference without Fundamental Frequency for End-to-End Pitch-controllable TTS

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.

Decoder Variational Inference

PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping

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.

Generative Adversarial Network Speech Synthesis

SANE-TTS: Stable And Natural End-to-End Multilingual Text-to-Speech

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.