uaMix-MAE: Efficient Tuning of Pretrained Audio Transformers with Unsupervised Audio Mixtures

Documenti analoghi

• LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes
  di: Dang, Trung, et al.
  Pubblicazione: (2024)
• ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation
  di: Bai, Yatong, et al.
  Pubblicazione: (2023)
• Zero-Shot Text-to-Speech from Continuous Text Streams
  di: Dang, Trung, et al.
  Pubblicazione: (2024)
• Single-channel speech enhancement using learnable loss mixup
  di: Chang, Oscar, et al.
  Pubblicazione: (2023)
• Weakly-supervised Audio Separation via Bi-modal Semantic Similarity
  di: Mahmud, Tanvir, et al.
  Pubblicazione: (2024)