Improving Noise Robustness of LLM-based Zero-shot TTS via Discrete Acoustic Token Denoising

Documenti analoghi

• SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features
  di: Shi, Yu-Fei, et al.
  Pubblicazione: (2024)
• DAIEN-TTS: Disentangled Audio Infilling for Environment-Aware Text-to-Speech Synthesis
  di: Lu, Ye-Xin, et al.
  Pubblicazione: (2025)
• BiVocoder: A Bidirectional Neural Vocoder Integrating Feature Extraction and Waveform Generation
  di: Du, Hui-Peng, et al.
  Pubblicazione: (2024)
• Pitch-and-Spectrum-Aware Singing Quality Assessment with Bias Correction and Model Fusion
  di: Shi, Yu-Fei, et al.
  Pubblicazione: (2024)
• ESTVocoder: An Excitation-Spectral-Transformed Neural Vocoder Conditioned on Mel Spectrogram
  di: Jiang, Xiao-Hang, et al.
  Pubblicazione: (2024)