← authors · overview

• From Audio to Semantics: Approaches to end-to-end spoken language understanding
  2018 · 139 citations
• DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement
  2021 · 35 citations
• Knowledge Transfer from Large-scale Pretrained Language Models to End-to-end Speech Recognizers
  2022 · 18 citations
• Multi-Dialect Speech Recognition With A Single Sequence-To-Sequence Model
  2017 · 10 citations
• Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration
  2025 · 2 citations
• SNRi Target Training for Joint Speech Enhancement and Recognition
  2021 · 1 citations
• WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iteration
  2022 · 1 citations
• Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations
  2023 · 1 citations
• SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping
  2022
• LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus
  2023
• FLEURS-R: A Restored Multilingual Speech Corpus for Generation Tasks
  2024
• Adaptive Dropout for Pruning Conformers
  2024