ToneCL: Contrastive Learning for Few-Shot Syllable-Level Tone Classification
Tone languages constitute over 50-70% of the world's languages, but the vast majority are low-resource, lacking the large transcribed corpora needed for automatic tone classification, so ToneCL is proposed, a lightweight contrastive learning framework for few-shot syllable-level tone classification.
Qi-Sheng Liao, Youngah Do
· 0 citations