Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks

Documenti analoghi

• Exploring the limits of decoder-only models trained on public speech recognition corpora
  di: Gupta, Ankit, et al.
  Pubblicazione: (2024)
• Improving Design of Input Condition Invariant Speech Enhancement
  di: Zhang, Wangyou, et al.
  Pubblicazione: (2024)
• Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Supervision, and LLM Mix-up Augmentation
  di: Wu, Shih-Lun, et al.
  Pubblicazione: (2023)
• Language model integration based on memory control for sequence to sequence speech recognition
  di: Cho, Jaejin, et al.
  Pubblicazione: (2018)
• A unified front-end framework for English text-to-speech synthesis
  di: Ying, Zelin, et al.
  Pubblicazione: (2023)