An openly released 630M-parameter BEST-RQ speech encoder, pretrained on 200k hours, matches state-of-the-art encoders on several ASR benchmarks and holds its own on ten SUPERB tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MERaLiON-SpeechEncoder: Towards a Speech Foundation Model for Singapore and Beyond
An openly released 630M-parameter BEST-RQ speech encoder, pretrained on 200k hours, matches state-of-the-art encoders on several ASR benchmarks and holds its own on ten SUPERB tasks.