Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducers

Documenti analoghi

• Hierarchical Recurrent Adapters for Efficient Multi-Task Adaptation of Large Speech Models
  di: Munkhdalai, Tsendsuren, et al.
  Pubblicazione: (2024)
• Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models
  di: Prabhavalkar, Rohit, et al.
  Pubblicazione: (2024)
• Aligner-Guided Training Paradigm: Advancing Text-to-Speech Models with Aligner Guided Duration
  di: Lou, Haowei, et al.
  Pubblicazione: (2024)
• SSPS: Self-Supervised Positive Sampling for Robust Self-Supervised Speaker Verification
  di: Lepage, Theo, et al.
  Pubblicazione: (2025)
• Piano Transcription by Hierarchical Language Modeling with Pretrained Roll-based Encoders
  di: Li, Dichucheng, et al.
  Pubblicazione: (2025)