Search Results for author:
Found 5 papers, 2 papers with code
Avocodo: Generative Adversarial Network for Artifact-free Vocoder
Therefore, in this paper, we investigate the relationship between these artifacts and GAN-based vocoders and propose a GAN-based vocoder, called Avocodo, that allows the synthesis of high-fidelity speech with reduced artifacts.
Enhancement of Pitch Controllability using Timbre-Preserving Pitch Augmentation in FastPitch
To address this issue, we propose two algorithms to improve the robustness of FastPitch.
FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis
Methods for modeling and controlling prosody with acoustic features have been proposed for neural text-to-speech (TTS) models.
N-Singer: A Non-Autoregressive Korean Singing Voice Synthesis System for Pronunciation Enhancement
N-Singer consists of a Transformer-based mel-generator, a convolutional network-based postnet, and voicing-aware discriminators.
A Neural Text-to-Speech Model Utilizing Broadcast Data Mixed with Background Music
Second, the GST-TTS model with an auxiliary quality classifier is trained with the filtered speech and a small amount of clean speech.
