ARCHI-TTS: A flow-matching-based Text-to-Speech Model with Self-supervised Semantic Aligner and Accelerated Inference

Documenti analoghi

• SemanticAudio: Audio Generation and Editing in Semantic Space
  di: Dai, Zheqi, et al.
  Pubblicazione: (2026)
• MusicScore: A Dataset for Music Score Modeling and Generation
  di: Lin, Yuheng, et al.
  Pubblicazione: (2024)
• Measuring Audio's Impact on Correctness: Audio-Contribution-Aware Post-Training of Large Audio Language Models
  di: He, Haolin, et al.
  Pubblicazione: (2025)
• ImmersiveFlow: Stereo-to-7.1.4 spatial audio generation with flow matching
  di: Liang, Zining, et al.
  Pubblicazione: (2026)
• CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis
  di: Wu, Chun Yat, et al.
  Pubblicazione: (2025)