Phonological-level Wav2Vec2 CTC framework for Mandarin MDD reduces FAR by 10.1% and DER by 23.6% versus phoneme baseline by jointly modeling segmental and tonal attributes.
Pitch-aware rnn-t for mandarin chinese mispronunciation detection and diagnosis,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Using Phonological-Level Wav2Vec2 for Mandarin Automatic Mispronunciation Detection and Diagnosis
Phonological-level Wav2Vec2 CTC framework for Mandarin MDD reduces FAR by 10.1% and DER by 23.6% versus phoneme baseline by jointly modeling segmental and tonal attributes.