Artificial Rigidities vs. Biological Noise: A Comparative Analysis of Multisensory Integration in AV-HuBERT and Human Observers
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917217515339776 |
|---|---|
| author | López, Francisco Portillo |
| author_facet | López, Francisco Portillo |
| contents | This study evaluates AV-HuBERT's perceptual bio-fidelity by benchmarking its response to incongruent audiovisual stimuli (McGurk effect) against human observers (N=44). Results reveal a striking quantitative isomorphism: AI and humans exhibited nearly identical auditory dominance rates (32.0% vs. 31.8%), suggesting the model captures biological thresholds for auditory resistance. However, AV-HuBERT showed a deterministic bias toward phonetic fusion (68.0%), significantly exceeding human rates (47.7%). While humans displayed perceptual stochasticity and diverse error profiles, the model remained strictly categorical. Findings suggest that current self-supervised architectures mimic multisensory outcomes but lack the neural variability inherent to human speech perception. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_15869 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Artificial Rigidities vs. Biological Noise: A Comparative Analysis of Multisensory Integration in AV-HuBERT and Human Observers López, Francisco Portillo Computation and Language Artificial Intelligence This study evaluates AV-HuBERT's perceptual bio-fidelity by benchmarking its response to incongruent audiovisual stimuli (McGurk effect) against human observers (N=44). Results reveal a striking quantitative isomorphism: AI and humans exhibited nearly identical auditory dominance rates (32.0% vs. 31.8%), suggesting the model captures biological thresholds for auditory resistance. However, AV-HuBERT showed a deterministic bias toward phonetic fusion (68.0%), significantly exceeding human rates (47.7%). While humans displayed perceptual stochasticity and diverse error profiles, the model remained strictly categorical. Findings suggest that current self-supervised architectures mimic multisensory outcomes but lack the neural variability inherent to human speech perception. |
| title | Artificial Rigidities vs. Biological Noise: A Comparative Analysis of Multisensory Integration in AV-HuBERT and Human Observers |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2601.15869 |