NAC adapts multi-scale RVQGAN audio codecs with kinematic-specific losses to produce ordered action tokens that yield lower reconstruction error and higher task success than prior tokenizers in VLA models.
Univnet: A neural vocoder with multi-resolution spectrogram discriminators for high-fidelity waveform generation.arXiv preprint arXiv:2106.07889
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
SwanVoice is a zero-shot TTS system for 1-4 speakers that reports higher richness and hierarchy scores than open-source baselines on monologue and dialogue tasks via mixed training and DiffusionNFT post-training.
Voice range indicates TTS model capability with VITS highest, Glow-TTS best at soft phonation, and CPPs of 7-8 dB marking natural quality while values over 10 dB sound robotic.
citing papers explorer
-
NAC: Neural Action Codec for Vision-Language-Action Models
NAC adapts multi-scale RVQGAN audio codecs with kinematic-specific losses to produce ordered action tokens that yield lower reconstruction error and higher task success than prior tokenizers in VLA models.
-
SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue
SwanVoice is a zero-shot TTS system for 1-4 speakers that reports higher richness and hierarchy scores than open-source baselines on monologue and dialogue tasks via mixed training and DiffusionNFT post-training.
-
Voice Mapping of Text-to-Speech Systems: A Metric-Based Approach for Voice Quality Assessment
Voice range indicates TTS model capability with VITS highest, Glow-TTS best at soft phonation, and CPPs of 7-8 dB marking natural quality while values over 10 dB sound robotic.
- A Survey of Advancing Audio Super-Resolution and Bandwidth Extension from Discriminative to Generative Models