Picture for Young-Ik Kim

Young-Ik Kim

N-Singer: A Non-Autoregressive Korean Singing Voice Synthesis System for Pronunciation Enhancement

Add code
Jun 29, 2021
Figure 1 for N-Singer: A Non-Autoregressive Korean Singing Voice Synthesis System for Pronunciation Enhancement
Figure 2 for N-Singer: A Non-Autoregressive Korean Singing Voice Synthesis System for Pronunciation Enhancement
Figure 3 for N-Singer: A Non-Autoregressive Korean Singing Voice Synthesis System for Pronunciation Enhancement
Figure 4 for N-Singer: A Non-Autoregressive Korean Singing Voice Synthesis System for Pronunciation Enhancement
Viaarxiv icon

FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis

Add code
Jun 29, 2021
Figure 1 for FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis
Figure 2 for FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis
Figure 3 for FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis
Figure 4 for FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis
Viaarxiv icon

A Neural Text-to-Speech Model Utilizing Broadcast Data Mixed with Background Music

Add code
Mar 04, 2021
Figure 1 for A Neural Text-to-Speech Model Utilizing Broadcast Data Mixed with Background Music
Figure 2 for A Neural Text-to-Speech Model Utilizing Broadcast Data Mixed with Background Music
Figure 3 for A Neural Text-to-Speech Model Utilizing Broadcast Data Mixed with Background Music
Figure 4 for A Neural Text-to-Speech Model Utilizing Broadcast Data Mixed with Background Music
Viaarxiv icon