62 citations · 124 across the 12 of their papers we have counts for
13 papers
Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec
Junhyeok Lee, Xiluo He, Jihwan Lee +6
Neural audio codecs optimized for mel-spectrogram reconstruction often fail to preserve intelligibility. While semantic encoder distillation improves encoded representations, it do…
Super Monotonic Alignment Search
Junhyeok Lee, Hyeongju Kim
Monotonic alignment search (MAS), introduced by Glow-TTS, is one of the most popular algorithm in text-to-speech to estimate unknown alignments between text and speech. Since this…
DualSpeech: Enhancing Speaker-Fidelity and Text-Intelligibility Through Dual Classifier-Free Guidance
Jinhyeok Yang, Junhyeok Lee, Hyeong-Seok Choi +3
Text-to-Speech (TTS) models have advanced significantly, aiming to accurately replicate human speech's diversity, including unique speaker identities and linguistic nuances. Despit…
JenGAN: Stacked Shifted Filters in GAN-Based Speech Synthesis
Hyunjae Cho, Junhyeok Lee, Wonbin Jung
Non-autoregressive GAN-based neural vocoders are widely used due to their fast inference speed and high perceptual quality. However, they often suffer from audible artifacts such a…
Diversifying and Expanding Frequency-Adaptive Convolution Kernels for Sound Event Detection
Hyeonuk Nam, Seong-Hu Kim, Deokki Min +2
Frequency dynamic convolution (FDY conv) has shown the state-of-the-art performance in sound event detection (SED) using frequency-adaptive kernels obtained by frequency-varying co…
VIFS: An End-to-End Variational Inference for Foley Sound Synthesis
Junhyeok Lee, Hyeonuk Nam, Yong-Hwa Park
The goal of DCASE 2023 Challenge Task 7 is to generate various sound clips for Foley sound synthesis (FSS) by "category-to-sound" approach. "Category" is expressed by a single inde…
PITS: Variational Pitch Inference without Fundamental Frequency for End-to-End Pitch-controllable TTS
Junhyeok Lee, Wonbin Jung, Hyunjae Cho +2
Previous pitch-controllable text-to-speech (TTS) models rely on directly modeling fundamental frequency, leading to low variance in synthesized speech. To address this issue, we pr…
PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping
Junhyeok Lee, Seungu Han, Hyunjae Cho +1
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 t…
NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates
Seungu Han, Junhyeok Lee
Conventionally, audio super-resolution models fixed the initial and the target sampling rates, which necessitate the model to be trained for each pair of sampling rates. We introdu…
Talking Face Generation with Multilingual TTS
Hyoung-Kyu Song, Sang Hoon Woo, Junhyeok Lee +5
In this work, we propose a joint system combining a talking face generation system with a text-to-speech system that can generate multilingual talking face videos from only the tex…
Controllable and Interpretable Singing Voice Decomposition via Assem-VC
Kang-wook Kim, Junhyeok Lee
We propose a singing decomposition system that encodes time-aligned linguistic content, pitch, and source speaker identity via Assem-VC. With decomposed speaker-independent informa…
NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling
Junhyeok Lee, Seungu Han
In this work, we introduce NU-Wave, the first neural audio upsampling model to produce waveforms of sampling rate 48kHz from coarse 16kHz or 24kHz inputs, while prior works could g…
Assem-VC: Realistic Voice Conversion by Assembling Modern Speech Synthesis Techniques
Kang-wook Kim, Seung-won Park, Junhyeok Lee +1
Recent works on voice conversion (VC) focus on preserving the rhythm and the intonation as well as the linguistic content. To preserve these features from the source, we decompose…