On a single-speaker MRI speech corpus, adding vocal-tract video to audio does not improve phoneme recognition, but attention analysis shows articulatory cues can lead acoustic cues in time.
Phoneme error rate (PER) The overall PER results on the held-out test set are presented in Table 1
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards disentangling the contributions of articulation and acoustics in multimodal phoneme recognition
On a single-speaker MRI speech corpus, adding vocal-tract video to audio does not improve phoneme recognition, but attention analysis shows articulatory cues can lead acoustic cues in time.