Lab LedgerDesk

Apple · Research ·

Compressing Streaming Neural Audio Encoders via Latent-Space Distillation

System-wide Dictation on Apple devices runs entirely on-device, and the speech it transcribes reaches the foundation model through a tokenizer: an encoder…

What moved

System-wide Dictation on Apple devices runs entirely on-device, and the speech it transcribes reaches the foundation model through a tokenizer: an encoder that maps short windows of waveform onto the representation the language model reads. …

Why it matters

Filed as a research filing from Apple, 2026-09-24. Tagged LLM.

On the record

  • Filed from the Apple official RSS on 2026-09-24.
  • Primary source host: machinelearning.apple.com.
  • The desk does not add a second source.
Primary source
machinelearning.apple.com
Desk
Logged as brief 222