collaborators
Showing eess.ASShow all

5 papers · 1 filter

eess.AS2025

Improving Test-Time Performance of RVQ-based Neural Codecs

Hyeongju Kim, Junhyeok Lee, Jacob Morton +2

The residual vector quantization (RVQ) technique plays a central role in recent advances in neural audio codecs. These models effectively synthesize high-fidelity audio from a limi…

eess.AS2025

Training Flow Matching Models with Reliable Labels via Self-Purification

Hyeongju Kim, Yechan Yu, June Young Yi +1

Training datasets are inherently imperfect, often containing mislabeled samples due to human annotation errors, limitations of tagging models, and other sources of noise. Such labe…

eess.AS2025

SupertonicTTS: Towards Highly Efficient and Streamlined Text-to-Speech System

Hyeongju Kim, Jinhyeok Yang, Yechan Yu +5

We introduce SupertonicTTS, a novel text-to-speech (TTS) system designed for efficient and streamlined speech synthesis. SupertonicTTS comprises three components: a speech autoenco…

eess.AS2025

Length-Aware Rotary Position Embedding for Text-Speech Alignment

Hyeongju Kim, Juheon Lee, Jinhyeok Yang +1

Many recent text-to-speech (TTS) systems are built on transformer architectures and employ cross-attention mechanisms for text-speech alignment. Within these systems, rotary positi…

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…