← authors · overview

• Zipformer: A faster and better encoder for automatic speech recognition
  2023 · 28 citations
• ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching
  2025 · 2 citations
• Delay-penalized transducer for low-latency streaming ASR
  2022 · 1 citations
• Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context
  2023 · 1 citations
• OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models
  2026
• Flow2GAN: Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-step High-Fidelity Audio Generation
  2025
• k2SSL: A Faster and Better Framework for Self-Supervised Speech Representation Learning
  2024
• CR-CTC: Consistency regularization on CTC for improved speech recognition
  2024
• Pruned RNN-T for fast, memory-efficient ASR training
  2022
• Fast and parallel decoding for transducer
  2022
• Blank-regularized CTC for Frame Skipping in Neural Transducer
  2023
• PromptASR for contextualized ASR with controllable style
  2023
• LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization
  2024