Metraipolis › archive › dc_34cd38c2ca59

Structured Phonological Representations for Audio-Articulatory rtMRI Speech Classification — arXiv:2608.09767

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.09767
License (as archived): CC0-1.0
Archived: 2026-10-19T08:50:29.181Z
SHA-256 of the archived text: 5c61cb43ccd8211a2d3a10fa03535c740b5ef5d6957c533ea7d46a29942c0cfc
Stable URL of this page: https://metraipolis.com/documento/dc_34cd38c2ca59

How to cite

Structured Phonological Representations for Audio-Articulatory rtMRI Speech Classification — arXiv:2608.09767 — arXiv (en), https://arxiv.org/abs/2608.09767 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_34cd38c2ca59 (Metraipolis archive dc_34cd38c2ca59, sha256 5c61cb43ccd8211a2d3a10fa03535c740b5ef5d6957c533ea7d46a29942c0cfc)

BibTeX

@misc{dc34cd38c2ca59,
  title = {Structured Phonological Representations for Audio-Articulatory rtMRI Speech Classification — arXiv:2608.09767},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.09767},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_34cd38c2ca59; sha256 5c61cb43ccd8211a2d3a10fa03535c740b5ef5d6957c533ea7d46a29942c0cfc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09767. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Real-time MRI makes it possible to observe vocal-tract articulation during speech, but mapping these articulatory patterns to phonetic and phonological categories remains challenging. We investigate whether PhonoQ, an audio-based model trained to recognize structured phonological features, provides useful information for audio--articulatory modeling. Specifically, we extract representations from PhonoQ's Conformer module, whose training is shaped by supervision for manner, place, voicing, and vowel features. Using articulatory contours with synchronized audio-derived features, we compare WavLM-large and HuBERT-large baselines with models that incorporate PhonoQ-derived representations. Across unseen-speech and unseen-subject settings, these features improve macro-F1 for phonological targets including manner, place, voicing, vowel height, and vowel backness, and also improve fine-grained 39-phoneme classification. In a contour-only inference setting, audio-derived teacher supervision yields modest but consistent gains over contour-only training, indicating that phonological information from synchronized audio can be partially transferred to articulatory models. Finally, posterior analyses show interpretable surface-sensitive patterns consistent with flapping-like /t/ realizations, /t/-/r/ retraction or affrication, and nasal place assimilation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Sound (cs.SD); Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2608.09767 — 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 2026-10-19T08:49:41.941Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).