Metraipolis › archive › dc_a73ef0023260
Mixture of Phonetic Experts Based Low-Rank Adaptation of Conformer Models for Accented English Speech Recognition — arXiv:2610.26888
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.26888
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-21T07:08:42.508Z
- SHA-256 of the archived text
d2a477163e9eb75c01372391bda58179c0e012be5c5efbaeee1301aa489bf165- Stable URL of this page
https://metraipolis.com/documento/dc_a73ef0023260
How to cite
Mixture of Phonetic Experts Based Low-Rank Adaptation of Conformer Models for Accented English Speech Recognition — arXiv:2610.26888 — arXiv (en), https://arxiv.org/abs/2610.26888 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a73ef0023260 (Metraipolis archive dc_a73ef0023260, sha256 d2a477163e9eb75c01372391bda58179c0e012be5c5efbaeee1301aa489bf165)
BibTeX
@misc{dca73ef0023260,
title = {Mixture of Phonetic Experts Based Low-Rank Adaptation of Conformer Models for Accented English Speech Recognition — arXiv:2610.26888},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.26888},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a73ef0023260; sha256 d2a477163e9eb75c01372391bda58179c0e012be5c5efbaeee1301aa489bf165},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.26888. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We present Mixture of Phonetic Experts based Low-Rank Adaptation (MoPE-LoRA), a parameter-efficient adaptation framework for accented English speech recognition. Recent mixture-of-experts approaches typically allocate experts per accent, implicitly treating accent identity as the primary axis of variation. In contrast, we organize adaptation along phonetic categories, motivated by the observation that accent differences are often expressed as systematic distortions of phoneme realization. MoPE-LoRA introduces a fixed set of six low-rank experts aligned with manner-of-articulation classes and performs frame-level routing through a hybrid mechanism that combines phoneme supervision with learned acoustic gating. Because the expert set is shared across accents, the model does not require accent-specific modules and naturally extends to previously unseen accents. Experiments on L2-ARCTIC show that MoPE-LoRA consistently improves over single LoRA and full fine-tuning. In zero-shot evaluation where one accent is held out during training, the proposed method yields a 12.3% relative improvement over single LoRA. These results indicate that phonetic-category-based decomposition offers a scalable and transferable alternative to accent-level adaptation. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Sound (cs.SD); Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2610.26888 — 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 2026-10-21T07:05:58.086Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).