Low resource cross-modal alignment using HGNN to enhance speech representation
Speech-text space alignment is a multimodal representation learning method consisting to map different speech and text into a shared representation space, leading to enrichment of the representation of each modality. Proposed architectures, such as SAMU-XLSR, typically follow a student/teacher framework, with the goal...
Y. Y. Nzeuhang, Marie Tahon, Paulin Melatagia Yonta
· 0 citations