Metraipolis › archive › dc_050d8754667c

Scalable Audio-LLM System for Speech MOS Evaluation: A Diagnostic Case Study and Adaptation Roadmap — arXiv:2610.41539

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41539
License (as archived)
CC0-1.0
Archived
2026-11-03T08:33:00.212Z
SHA-256 of the archived text
7d19ecd131a139b34de0489c8e147f6489ec6b65dd05a0ee011a6fddc5ed0329
Stable URL of this page
https://metraipolis.com/documento/dc_050d8754667c

How to cite

Scalable Audio-LLM System for Speech MOS Evaluation: A Diagnostic Case Study and Adaptation Roadmap — arXiv:2610.41539 — arXiv (en), https://arxiv.org/abs/2610.41539 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_050d8754667c (Metraipolis archive dc_050d8754667c, sha256 7d19ecd131a139b34de0489c8e147f6489ec6b65dd05a0ee011a6fddc5ed0329)
BibTeX
@misc{dc050d8754667c,
  title = {Scalable Audio-LLM System for Speech MOS Evaluation: A Diagnostic Case Study and Adaptation Roadmap — arXiv:2610.41539},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41539},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_050d8754667c; sha256 7d19ecd131a139b34de0489c8e147f6489ec6b65dd05a0ee011a6fddc5ed0329},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41539. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The continuous deployment of enterprise voice systems creates a critical operational bottleneck: evaluating the acoustic quality of synthetic speech across high-volume production updates. While human Mean Opinion Score (MOS) remains the quality gold standard, it introduces severe operational costs and turn-around delays that make continuous integration infeasible. In this work, we present a system design case study for a scalable, low-cost and offline evaluation pipeline capable of scoring large batches of synthetic speech at marginal cost. First, we use Qwen2-Audio-7B-Instruct in a zero-shot setting for granular MOS estimation, noticing perceptual blind spots and inherent biases. Then, we analyze SOMOS dataset and construct a diagnostic benchmark that operationalizes two prosodic dimensions associated with human naturalness ratings. Finally, we adapt Qwen2-Audio-7B-Instruct through a parameter-efficient finetuning (LoRA) on the task of MOS evaluation, observing improvements over base model and widely used neural baselines like UTMOS and establishing a practical blueprint for enterprise-grade speech quality assurance.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv eess.AS, nuovi lavori del giorno).
Categorie arXiv: Sound (cs.SD) ; Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2610.41539 — 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 2026-11-03T08:15:54.220Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).