Combining frozen speech SSL/Whisper features with phoneme-level BERT features improves automatic Japanese prosody label prediction over either input alone.
*”: Other symbol that was neither a high-low transition nor a phrase boundary. • “[
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Prosody Labeling with Phoneme-BERT and Speech Foundation Models
Combining frozen speech SSL/Whisper features with phoneme-level BERT features improves automatic Japanese prosody label prediction over either input alone.