A tone-conditioned curriculum framework with gated adapters achieves 28.41% average WER on six Southern Bantu languages, showing architecture-specific performance differences between W2V-BERT and Whisper.
They remain primarily oral, and tone and prosody encode grammatical and cultural distinctions not fully captured in writing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Tone-Conditioned Curriculum Learning for Low-Resource Bantu Speech Recognition
A tone-conditioned curriculum framework with gated adapters achieves 28.41% average WER on six Southern Bantu languages, showing architecture-specific performance differences between W2V-BERT and Whisper.