Why Do Speech Language Models Fail to Generate Semantically Coherent Outputs? A Modality Evolving Perspective

Documenti analoghi

• LSCodec: Low-Bitrate and Speaker-Decoupled Discrete Speech Codec
  di: Guo, Yiwei, et al.
  Pubblicazione: (2024)
• Attention-Constrained Inference for Robust Decoder-Only Text-to-Speech
  di: Wang, Hankun, et al.
  Pubblicazione: (2024)
• VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech
  di: Du, Chenpeng, et al.
  Pubblicazione: (2024)
• Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency
  di: Wang, Haoran, et al.
  Pubblicazione: (2025)
• Acoustic BPE for Speech Generation with Discrete Tokens
  di: Shen, Feiyu, et al.
  Pubblicazione: (2023)