JCAPT, a Mamba-based joint APA and MDD model with phonological features and think tokens, improves mispronunciation detection and several scoring aspects on speechocean762 over JAM.
Elsa speak app: Automatic speech recognition (asr) for supplementing english pronunciation skills,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
JCAPT: A Joint Modeling Approach for CAPT
JCAPT, a Mamba-based joint APA and MDD model with phonological features and think tokens, improves mispronunciation detection and several scoring aspects on speechocean762 over JAM.