Смешивание многообразий речи и текста
method
ID: speechtextmanifoldmixup
Related Papers
STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation
AbstractHow to learn a better speech representation for end-to-end speech-to-text translation (ST) with limited labeled data? Existing techniques often attempt to transfer powerful machine translation (MT) capabilities to ST, but …...