collaborators
Showing eess.ASShow all

5 papers · 1 filter

eess.AS2026

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…

eess.AS2026

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…

eess.AS2024

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…

eess.AS2024

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…

eess.AS2024

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…