Metraipolis › archive › dc_85b76016c8a4

UniAE-MoE: A Unified Audio Encoder via Mixture of Experts — arXiv:2609.39199

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.39199
License (as archived): CC0-1.0
Archived: 2026-10-07T12:45:02.135Z
SHA-256 of the archived text: 715c906dd14c88afe583fa56fa0b90fb1bdd0063b7ef6125aa420acdb339b5ac
Stable URL of this page: https://metraipolis.com/documento/dc_85b76016c8a4

How to cite

UniAE-MoE: A Unified Audio Encoder via Mixture of Experts — arXiv:2609.39199 — arXiv (en), https://arxiv.org/abs/2609.39199 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_85b76016c8a4 (Metraipolis archive dc_85b76016c8a4, sha256 715c906dd14c88afe583fa56fa0b90fb1bdd0063b7ef6125aa420acdb339b5ac)

BibTeX

@misc{dc85b76016c8a4,
  title = {UniAE-MoE: A Unified Audio Encoder via Mixture of Experts — arXiv:2609.39199},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39199},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_85b76016c8a4; sha256 715c906dd14c88afe583fa56fa0b90fb1bdd0063b7ef6125aa420acdb339b5ac},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39199. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Audio Language Models (LALMs) rely on effective audio encoders for multi-task performance. We introduce UniAE-MoE, a unified audio encoder designed to model cross-domain audio representations and achieve outstanding downstream understanding performance via a Mixture-of-Experts (MoE) architecture. Specifically, we explore mainstream audio encoders and integrate those from Qwen2-Audio and Audio-Flamingo 3, which demonstrate superior downstream capabilities. To facilitate effective model fusion, we improve our encoder using SwiGLU with shared experts to decouple encoder networks, and we further introduce a two-stage instruction-tuning strategy to better adapt the model to diverse downstream tasks. Moreover, we propose the task-specific data scaling (TSDS) technique to enhance UniAE-MoE's understanding capabilities. On the XARES-LLM benchmark, UniAE-MoE attains a score of 0.802, achieving state-of-the-art performance. It also delivers top-tier performance in the official Interspeech 2026 Audio Encoder Capability Challenge, further demonstrating robust generalization across diverse audio tasks. Together, these results validate the effectiveness of UniAE-MoE for unified audio understanding across speech, music, and general audio domains.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.39199 — 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 2026-10-07T12:14:14.034Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).