← authors · overview

• Improving Trajectory Modelling for DNN-based Speech Synthesis by using Stacked Bottleneck Features and Minimum Generation Error Training
  2016 · 24 citations
• DualCodec: A Low-Frame-Rate, Semantically-Enhanced Neural Audio Codec for Speech Generation
  2025 · 21 citations
• NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations
  2025 · 15 citations
• TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling
  2025 · 9 citations
• The Singing Voice Conversion Challenge 2025: From Singer Identity Conversion To Singing Style Conversion
  2025 · 5 citations
• TASLA: Text-Aligned Speech Tokens with Multiple Layer-Aggregation
  2025 · 2 citations
• AnyAccomp: Generalizable Accompaniment Generation via Quantized Melodic Bottleneck
  2025 · 2 citations
• Multi-Metric Preference Alignment for Generative Speech Restoration
  2025
• HiFi-Glot: High-Fidelity Neural Formant Synthesis with Differentiable Resonant Filters
  2024