Dynamic Acoustic Model Architecture Optimization in Training for ASR

Documenti analoghi

• Efficient Supernet Training with Orthogonal Softmax for Scalable ASR Model Compression
  di: Xu, Jingjing, et al.
  Pubblicazione: (2025)
• Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition
  di: Xu, Jingjing, et al.
  Pubblicazione: (2024)
• Text-Utilization for Encoder-dominated Speech Recognition Models
  di: Zeyer, Albert, et al.
  Pubblicazione: (2026)
• Diffusion Language Models for Speech Recognition
  di: Naveriani, Davyd, et al.
  Pubblicazione: (2026)
• On the Relation between Internal Language Model and Sequence Discriminative Training for Neural Transducers
  di: Yang, Zijian, et al.
  Pubblicazione: (2023)