← authors · overview

• FINALLY: fast and universal speech enhancement with studio-like quality
  2024 · 3 citations
• How Can Incentives and Cut Layer Selection Influence Data Contribution in Split Federated Learning?
  2024 · 1 citations
• Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition
  2026
• Shallow quantum circuit for generating extremely low-entangled approximate state designs
  2025
• DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correction
  2025
• Geometry-Preserving Encoder/Decoder in Latent Generative Models
  2025
• Speak & Spell: LLM-Driven Controllable Phonetic Error Augmentation for Robust Dialogue State Tracking
  2024
• Monotone Generative Modeling via a Gromov-Monge Embedding
  2023
• Optimizing Two-Pass Cross-Lingual Transfer Learning: Phoneme Recognition and Phoneme to Grapheme Translation
  2023
• Acoustic Feature Mixup for Balanced Multi-aspect Pronunciation Assessment
  2024
• Enhancing Dialogue Speech Recognition with Robust Contextual Awareness via Noise Representation Learning
  2024
• Pseudochaotic Many-Body Dynamics as a Pseudorandom State Generator
  2024
• FRIDAY: Mitigating Unintentional Facial Identity in Deepfake Detectors Guided by Facial Recognizers
  2024