PTLOC adds per-source local constraints to self-supervised acoustic pre-training via first-order MAML-style updates, reporting improved downstream ASR word error rates over a baseline that is not compute-matched.
One is a self-supervised English acoustic model pre-training using speech data from multiple domains based on BEST-RQ [4]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
support 1representative citing papers
citing papers explorer
-
Heterogeneous Self-Supervised Acoustic Pre-Training with Local Constraints
PTLOC adds per-source local constraints to self-supervised acoustic pre-training via first-order MAML-style updates, reporting improved downstream ASR word error rates over a baseline that is not compute-matched.