← authors · overview

• DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion
  2025 · 51 citations
• Voice activity detection in the wild: A data-driven approach using teacher-student training
  2021 · 34 citations
• SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement
  2025 · 16 citations
• BUT System for the Second DIHARD Speech Diarization Challenge
  2020 · 5 citations
• WEST: LLM based Speech Toolkit for Speech Understanding, Generation, and Interaction
  2025 · 1 citations
• WenetSpeech-Chuan: A Large-Scale Sichuanese Corpus with Rich Annotation for Dialectal Speech Processing
  2025
• Direct Preference Optimization for Speech Autoregressive Diffusion Models
  2025
• SenSE: Semantic-Aware High-Fidelity Universal Speech Enhancement
  2025
• Hybrid Pruning: In-Situ Compression of Self-Supervised Speech Models for Speaker Verification and Anti-Spoofing
  2025
• Traceable TTS: Toward Watermark-Free TTS with Strong Traceability