the.ai

Speech / Representation

verified

Speech Representation Learning

Transcribed speech is expensive and raw audio is nearly free. Self-supervised speech models learn from the audio alone — hide parts of it, learn to identify what was hidden — and the representations that fall out turn an hour of labelled data into a usable recogniser. The pretext task is throwaway; what is kept is the encoder underneath it.

Viz primitive · budget-splitmasked-frames = 48

masked-frames holds 48% of the budget; rest holds the remaining 52%.

Latent frames hidden from the model against frames left visible, in frames. Drag the masked frames up to watch the pretext task get harder — too few and the neighbouring audio gives the answer away, and past about half there is little context left to answer from.

48

Reviewed by opendroid · 2026-08-18

  • arXiv:2006.11477 — wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
  • arXiv:2106.07447 — HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units