research
∙
12/13/2022
Towards trustworthy phoneme boundary detection with autoregressive model and improved evaluation metric
Phoneme boundary detection has been studied due to its central role in v...
share
research
∙
11/17/2022
NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis
Various applications of voice synthesis have been developed independentl...
research
∙
04/07/2022
Expressive Singing Synthesis Using Local Style Token and Dual-path Pitch Encoder
This paper proposes a controllable singing voice synthesis system capabl...
research
∙
10/27/2021
Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations
We present a neural analysis and synthesis (NANSY) framework that can ma...
research
∙
05/28/2021
Differentiable Artificial Reverberation
We propose differentiable artificial reverberation (DAR), a family of ar...
research
∙
04/21/2021
Room adaptive conditioning method for sound event classification in reverberant environments
Ensuring performance robustness for a variety of situations that can occ...
research
∙
02/05/2021
Real-time Denoising and Dereverberation with Tiny Recurrent U-Net
Modern deep learning-based models have seen outstanding performance impr...
research
∙
08/11/2020
Exploring Aligned Lyrics-Informed Singing Voice Separation
In this paper, we propose a method of utilizing aligned lyrics as additi...
research
∙
06/01/2020
Phase-aware Single-stage Speech Denoising and Dereverberation with U-Net
In this work, we tackle a denoising and dereverberation problem with a s...
research
∙
04/13/2020
From Inference to Generation: End-to-end Fully Self-supervised Generation of Human Face from Speech
This work seeks the possibility of generating the human face from voice ...
research
∙
10/29/2019
Disentangling Timbre and Singing Style with Multi-singer Singing Synthesis System
In this study, we define the identity of the singer with two independent...
research
∙
08/19/2019
Audio query-based music source separation
In recent years, music source separation has been one of the most intens...
research
∙
08/06/2019
Adversarially Trained End-to-end Korean Singing Voice Synthesis System
In this paper, we propose an end-to-end Korean singing voice synthesis s...
research
∙
03/07/2019