Sang-Hoon Lee

Assistant Professor, Ajou University

2 papers at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

1 paper

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Streaming Audio Generation from Discrete Tokens via Streaming Flow Matching

#3604 · Ha-Yeong Choi, Sang-Hoon Lee

We introduce Streaming Flow Matching, a novel streaming generative model for real-time audio generation from discrete tokens.

Poster Session 3

1 paper

Thursday, December 4, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

CoreaSpeech: Korean Speech Corpus via JAMO-based Coreset Selection for Efficient and Robust Korean Speech Generation

#1916 · Ki-Joong Kwon, Jun-Ho So, Sang-Hoon Lee

We introduce CoreaSpeech, a publicly released 700 h Korean TTS corpus built via a Korean-specific text normalizer and a novel jamo-based coreset selection pipeline.