Title resolution pending

Introduction Self-Supervised Learning (SSL) is the process of training a model where the targets are derived directly from the input data itself, decreasing the need of human-label

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

1 Pith paper citing it

browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

representative citing papers

Towards Early Prediction of Self-Supervised Speech Model Performance

cs.SD · 2025-01-10 · conditional · novelty 5.0

Rank and clustering metrics on SSL speech embeddings predict downstream ASR and SV performance better than the pre-training loss, especially for in-domain ASR.

citing papers explorer

Showing 1 of 1 citing paper.

Towards Early Prediction of Self-Supervised Speech Model Performance cs.SD · 2025-01-10 · conditional · none · ref 1
Rank and clustering metrics on SSL speech embeddings predict downstream ASR and SV performance better than the pre-training loss, especially for in-domain ASR.

Title resolution pending

fields

years

verdicts

representative citing papers

citing papers explorer