A challenge systems paper reporting the top-scoring ML-SUPERB 2.0 entry, built from a hybrid language identifier and a per-language selection of three pretrained ASR models.
This dataset combines various multilingual speech corpora and covers 141 of the 153 target languages
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
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
TalTech Systems for the Interspeech 2025 ML-SUPERB 2.0 Challenge
A challenge systems paper reporting the top-scoring ML-SUPERB 2.0 entry, built from a hybrid language identifier and a per-language selection of three pretrained ASR models.