(April 2021) DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement

• audio samples

(April 2022) SNRi Target Training for Joint Speech Enhancement and Recognition

• audio samples

(Oct 2022) WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iteration

• audio samples

(Mar 2023) Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations

• audio samples

(May 2023) LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus

• audio samples using Google internal toolkits
• audio samples using OSS toolkits (ESPnet, kan-bayashi/ParallelWaveGAN)

(Mar 2025) Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration

• audio samples

(Mar 2025) ReverbMiipher: Generative Speech Restoration meets Reverberation Characteristics Controllability

• audio samples, visualization, demo

(Mar 2025) Source Separation by Flow Matching

• audio samples