← authors · overview

• OLKAVS: An Open Large-scale Korean Audio-visual Speech Dataset
  2023 · 6 citations
• Opening the Black Box of wav2vec Feature Encoder
  2022 · 4 citations
• Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessment
  2025 · 2 citations
• Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study
  2023 · 2 citations
• OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer
  2024 · 2 citations
• CS-FLEURS: A Massively Multilingual and Code-Switched Speech Dataset
  2025
• On-device Streaming Discrete Speech Units
  2025
• Distilling a Pretrained Language Model to a Multilingual ASR Model
  2022
• Automatic Severity Classification of Dysarthric speech by using Self-supervised Model with Multi-task Learning
  2022
• Unsupervised Speech Representation Pooling Using Vector Quantization
  2023
• Self-Supervised Speech Representations are More Phonetic than Semantic
  2024
• On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models
  2024
• ESPnet-EZ: Python-only ESPnet for Easy Fine-tuning and Integration
  2024