Scaling weak supervision to 680k hours of multilingual audio produces zero-shot speech recognition models competitive with fully supervised systems.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2022 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Robust Speech Recognition via Large-Scale Weak Supervision
Scaling weak supervision to 680k hours of multilingual audio produces zero-shot speech recognition models competitive with fully supervised systems.