FLToP CTC: Frame-Level Token Pruning via Relative Threshold for Efficient and Memory-Saving Decoding on Diverse Platforms

Documenti analoghi

• CTC Blank Triggered Dynamic Layer-Skipping for Efficient CTC-based Speech Recognition
  di: Hou, Junfeng, et al.
  Pubblicazione: (2024)
• kNN-CTC: Enhancing ASR via Retrieval of CTC Pseudo Labels
  di: Zhou, Jiaming, et al.
  Pubblicazione: (2023)
• Decoder-only Architecture for Speech Recognition with CTC Prompts and Text Data Augmentation
  di: Tsunoo, Emiru, et al.
  Pubblicazione: (2023)
• Guiding Frame-Level CTC Alignments Using Self-knowledge Distillation
  di: Kim, Eungbeom, et al.
  Pubblicazione: (2024)
• Joint Beam Search Integrating CTC, Attention, and Transducer Decoders
  di: Sudo, Yui, et al.
  Pubblicazione: (2024)