Metraipolis › archive › dc_596f341d4f32
Indic-CLAP: Text--Audio Understanding in Indic Languages via Cross-Lingual Distillation — arXiv:2610.08846
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.08846
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T14:17:22.601Z
- SHA-256 of the archived text
e789e3caedb76f0daceddcbd1f25a5875fb6605c382c1a74057254bbd6536f9a- Stable URL of this page
https://metraipolis.com/documento/dc_596f341d4f32
How to cite
Indic-CLAP: Text--Audio Understanding in Indic Languages via Cross-Lingual Distillation — arXiv:2610.08846 — arXiv (en), https://arxiv.org/abs/2610.08846 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_596f341d4f32 (Metraipolis archive dc_596f341d4f32, sha256 e789e3caedb76f0daceddcbd1f25a5875fb6605c382c1a74057254bbd6536f9a)
BibTeX
@misc{dc596f341d4f32,
title = {Indic-CLAP: Text--Audio Understanding in Indic Languages via Cross-Lingual Distillation — arXiv:2610.08846},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.08846},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_596f341d4f32; sha256 e789e3caedb76f0daceddcbd1f25a5875fb6605c382c1a74057254bbd6536f9a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08846. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Contrastive Language--Audio Pretraining (CLAP) learns a joint text--audio representation space, which enables zero-shot audio understanding from natural-language descriptions. However, its English-only text encoder restricts CLAP to tasks and datasets expressed in English. We present Indic-CLAP, a multilingual text--audio model that extends CLAP to nine Indic languages spoken by over a billion people. Exploiting CLAP's dual-encoder structure, we propose to train only an Indic text encoder by distillation while keeping the audio encoder frozen, using machine-translated AudioCaps captions. We compare distillation from CLAP's text encoder, audio encoder, and a novel hybrid objective combining both. Our evaluation shows that the Indic-CLAP encoder inherits the cross-modal alignment from the CLAP teacher, as evidenced by the performance on cross-modal retrieval and zero-shot classification tasks. Further, we study the cross-modal alignment using modality gap analysis, which explains the performance trends. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv eess.AS, nuovi lavori del giorno). Categorie arXiv: Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2610.08846 — 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 2026-10-08T13:29:00.750Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).