Metraipolis › archive › dc_7d1c91e249af

Enhancing speech representation learning with cross-modal knowledge transfer with HGNN under low resource settings: the case study of Yemba — arXiv:2609.23194

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.23194
License (as archived)
CC0-1.0
Archived
2026-10-09T06:49:45.969Z
SHA-256 of the archived text
ed908b79592a4b45261908bab73c4dafbd4dfe2bd19926a09d6d4c0bf344c3f3
Stable URL of this page
https://metraipolis.com/documento/dc_7d1c91e249af

How to cite

Enhancing speech representation learning with cross-modal knowledge transfer with HGNN under low resource settings: the case study of Yemba — arXiv:2609.23194 — arXiv (en), https://arxiv.org/abs/2609.23194 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7d1c91e249af (Metraipolis archive dc_7d1c91e249af, sha256 ed908b79592a4b45261908bab73c4dafbd4dfe2bd19926a09d6d4c0bf344c3f3)
BibTeX
@misc{dc7d1c91e249af,
  title = {Enhancing speech representation learning with cross-modal knowledge transfer with HGNN under low resource settings: the case study of Yemba — arXiv:2609.23194},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23194},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7d1c91e249af; sha256 ed908b79592a4b45261908bab73c4dafbd4dfe2bd19926a09d6d4c0bf344c3f3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23194. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Acoustic representation learning is crucial for speech processing, yet low-resource languages (LRLs) face severe data scarcity, limiting the effectiveness of traditional and self-supervised methods. As a promising alternative, in this work, we propose to enhance acoustic representation trough a cross-modal transfer knowledge approach, based on heterogeneous graph neural networks (HGNNs), where acoustic and linguistic entities are modeled as distinct node types within a unified graph. Through message-passing mechanisms, linguistic nodes explicitly transfer knowledge to acoustic nodes, enabling structured and interpretable cross-modal information flow. To highlight this knowledge transfer and its benefits, we measured standard clustering metrics as an intrinsic evaluation of acoustic representation, and to emphasize applicability, we performed isolated-word recognition tasks using an English benchmark and a Cameroonian language dataset in low resources settings . Results demonstrate that acoustic representations consistently benefit from linguistic knowledge propagated through the graph. To our knowledge, this is the first demonstration of explicit cross-modal knowledge transfer for acoustic representation learning using HGNNs, highlighting a promising direction for speech representation in low-resource settings.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.23194 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T06:48:44.980Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).