Multimodal pre-training across EMA, MRI, and EMG articulatory streams cuts MRI-to-speech word error rate from 69.5% to 33.4% in a single-speaker low-resource setting, with similar gains for EMG-to-speech.
When training the encoder, like [3], we randomly crop a 0.6 to 2.0 second window from each sample in the size-64 batch, with the window length fixed within the batch
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
eess.AS 1years
2024 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Deep Speech Synthesis from Multimodal Articulatory Representations
Multimodal pre-training across EMA, MRI, and EMG articulatory streams cuts MRI-to-speech word error rate from 69.5% to 33.4% in a single-speaker low-resource setting, with similar gains for EMG-to-speech.