[First-Authored Papers] - LAMA-UT: Language Agnostic Multilingual ASR through Orthography Unification and Language-Specific Transliteration (AAAI 2025 Oral) - UniCoM: A Universal Code-Switching Speech Generator (EMNLP 2025 Findings) - SAGE-LD: Towards Scalable and Generalizable End-to-End Language Diarization via Simulated Data Augmentation (Preprint) - UR-BERT: Scaling Text Encoders for Massively Multilingual TTS Through Universal Romanization and Speech Token Prediction (Interspeech 2026) - MoLGE: Mixture of Language Group Experts for Efficient Scaling of Massively Multilingual Speech Recognition (Under Review) [Co-Authored Papers] - Talk3d: High-fidelity talking portrait synthesis via personalized 3D generative prior (Preprint) - UniverSR: Unified and Versatile Audio Super-Resolution via Vocoder-Free Flow Matching (ICASSP 2026) [CV] - Full curriculum vitae: https://sanghyang00.github.io/