Metraipolis › archive › dc_da0c499de04d

Objective Intelligibility Prediction Using Distance Metrics on Speech Foundation Model Representations — arXiv:2609.13046

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13046
License (as archived)
CC0-1.0
Archived
2026-10-16T05:10:08.595Z
SHA-256 of the archived text
cbb8faf2cdcaa03141db1672c9b2b2f0fe82cc8e5533a7605fa2dc9efd2bc577
Stable URL of this page
https://metraipolis.com/documento/dc_da0c499de04d

How to cite

Objective Intelligibility Prediction Using Distance Metrics on Speech Foundation Model Representations — arXiv:2609.13046 — arXiv (en), https://arxiv.org/abs/2609.13046 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da0c499de04d (Metraipolis archive dc_da0c499de04d, sha256 cbb8faf2cdcaa03141db1672c9b2b2f0fe82cc8e5533a7605fa2dc9efd2bc577)
BibTeX
@misc{dcda0c499de04d,
  title = {Objective Intelligibility Prediction Using Distance Metrics on Speech Foundation Model Representations — arXiv:2609.13046},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13046},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da0c499de04d; sha256 cbb8faf2cdcaa03141db1672c9b2b2f0fe82cc8e5533a7605fa2dc9efd2bc577},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13046. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

High-dimensional representations of pretrained speech foundation models have proven beneficial for objective speech quality and intelligibility prediction. While existing work on neural intelligibility prediction usually leverages such representations for task-specific fine-tuning, in this work we evaluate the usefulness of such representations for intelligibility prediction without any further training. We conduct a layer-wise analysis of multiple speech foundation models, correlating various embedding distances with subjective intelligibility scores. The results show that embeddings extracted from Whisper speech recognition models are best suited, with the last encoder and decoder layers yielding the best correlations when using the Fréchet Audio Distance. Notably, the evaluated distances outperform classical intelligibility metrics and are more robust than Word and Character Error Rates. Further, correlations improve with increasing size of the Whisper model from which embeddings are extracted.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in eess.AS).
Categorie arXiv: Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2609.13046 — 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 2026-10-16T04:52:10.835Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).