A new semi-supervised ASR framework, TopIPL, combines a dynamic pseudo-label cache and top-N checkpoint teacher averaging to improve WER by up to 40 percent in low-resource settings.
Our approach can be applicable to any language and integrates NeMo tools, including the Speech Data Processor (SDP) 3, to automate data collection and preprocessing
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
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Unified Semi-Supervised Pipeline for Automatic Speech Recognition
A new semi-supervised ASR framework, TopIPL, combines a dynamic pseudo-label cache and top-N checkpoint teacher averaging to improve WER by up to 40 percent in low-resource settings.