SummaryMixing: A Linear-Complexity Alternative to Self-Attention for Speech Recognition and Understanding

Documenti analoghi

• Linear Time Complexity Conformers with SummaryMixing for Streaming Speech Recognition
  di: Parcollet, Titouan, et al.
  Pubblicazione: (2024)
• Linear-Complexity Self-Supervised Learning for Speech Processing
  di: Zhang, Shucong, et al.
  Pubblicazione: (2024)
• Loquacious Set: 25,000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use
  di: Parcollet, Titouan, et al.
  Pubblicazione: (2025)
• Benchmarking Rotary Position Embeddings for Automatic Speech Recognition
  di: Zhang, Shucong, et al.
  Pubblicazione: (2025)
• Evaluation of LLMs in Speech is Often Flawed: Test Set Contamination in Large Language Models for Speech Recognition
  di: Tseng, Yuan, et al.
  Pubblicazione: (2025)