Picture for Junhyeok Lee

Junhyeok Lee

JenGAN: Stacked Shifted Filters in GAN-Based Speech Synthesis

Add code
Jun 10, 2024
Viaarxiv icon

Diversifying and Expanding Frequency-Adaptive Convolution Kernels for Sound Event Detection

Jun 08, 2024
Viaarxiv icon

LLM-Based Cooperative Agents using Information Relevance and Plan Validation

May 27, 2024
Viaarxiv icon

LatentSwap: An Efficient Latent Code Mapping Framework for Face Swapping

Add code
Mar 02, 2024
Viaarxiv icon

VIFS: An End-to-End Variational Inference for Foley Sound Synthesis

Add code
Jun 08, 2023
Figure 1 for VIFS: An End-to-End Variational Inference for Foley Sound Synthesis
Figure 2 for VIFS: An End-to-End Variational Inference for Foley Sound Synthesis
Figure 3 for VIFS: An End-to-End Variational Inference for Foley Sound Synthesis
Figure 4 for VIFS: An End-to-End Variational Inference for Foley Sound Synthesis
Viaarxiv icon

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

Add code
Mar 02, 2023
Figure 1 for PITS: Variational Pitch Inference without Fundamental Frequency for End-to-End Pitch-controllable TTS
Figure 2 for PITS: Variational Pitch Inference without Fundamental Frequency for End-to-End Pitch-controllable TTS
Figure 3 for PITS: Variational Pitch Inference without Fundamental Frequency for End-to-End Pitch-controllable TTS
Figure 4 for PITS: Variational Pitch Inference without Fundamental Frequency for End-to-End Pitch-controllable TTS
Viaarxiv icon

Designing an offline reinforcement learning objective from scratch

Add code
Jan 30, 2023
Figure 1 for Designing an offline reinforcement learning objective from scratch
Figure 2 for Designing an offline reinforcement learning objective from scratch
Figure 3 for Designing an offline reinforcement learning objective from scratch
Figure 4 for Designing an offline reinforcement learning objective from scratch
Viaarxiv icon

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

Add code
Nov 08, 2022
Figure 1 for PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping
Figure 2 for PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping
Figure 3 for PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping
Figure 4 for PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping
Viaarxiv icon

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

Add code
Jun 24, 2022
Figure 1 for SANE-TTS: Stable And Natural End-to-End Multilingual Text-to-Speech
Figure 2 for SANE-TTS: Stable And Natural End-to-End Multilingual Text-to-Speech
Figure 3 for SANE-TTS: Stable And Natural End-to-End Multilingual Text-to-Speech
Figure 4 for SANE-TTS: Stable And Natural End-to-End Multilingual Text-to-Speech
Viaarxiv icon

Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization

Add code
Jun 17, 2022
Figure 1 for Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization
Figure 2 for Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization
Figure 3 for Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization
Figure 4 for Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization
Viaarxiv icon