← authors · overview

• CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech
  2025 · 15 citations
• Direct Preference-based Policy Optimization without Reward Modeling
  2023 · 5 citations
• Assem-VC: Realistic Voice Conversion by Assembling Modern Speech Synthesis Techniques
  2021 · 3 citations
• Super Monotonic Alignment Search
  2024 · 1 citations
• PITS: Variational Pitch Inference without Fundamental Frequency for End-to-End Pitch-controllable TTS
  2023 · 1 citations
• Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec
  2026
• Motif-2-12.7B-Reasoning: A Practitioner's Guide to RL Training Recipes
  2025
• Expanding Foundational Language Capabilities in Open-Source LLMs through a Korean Case Study
  2025
• MaskVCT: Masked Voice Codec Transformer for Zero-Shot Voice Conversion With Increased Controllability via Multiple Guidances
  2025
• Improving Test-Time Performance of RVQ-based Neural Codecs
  2025
• Motif 2.6B Technical Report
  2025
• Motif 2 12.7B technical report
  2025
• Controllable and Interpretable Singing Voice Decomposition via Assem-VC
  2021
• Talking Face Generation with Multilingual TTS
  2022
• NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates
  2022