Pith. sign in

An unsuper- vised autoregressive model for speech representation learning,

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.SD 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Effective Context in Neural Speech Models

cs.SD · 2025-05-28 · conditional · novelty 6.0

Introduces truncation and Jacobian-based measures of effective context showing that self-supervised speech Transformers use a short, mostly local context and can be streamed with minor probing degradation.

citing papers explorer

Showing 1 of 1 citing paper.

  • Effective Context in Neural Speech Models cs.SD · 2025-05-28 · conditional · none · ref 6

    Introduces truncation and Jacobian-based measures of effective context showing that self-supervised speech Transformers use a short, mostly local context and can be streamed with minor probing degradation.