A grapheme-conditioned annotation model improves grapheme-phoneme consistency of TTS labels, but the primary metric is partly enforced by the dictionary constraint rather than learned.
Applying this method to downstream tasks be- yond textual accent estimation is a challenge for future work
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Grapheme-Coherent Phonemic and Prosodic Annotation of Speech by Implicit and Explicit Grapheme Conditioning
A grapheme-conditioned annotation model improves grapheme-phoneme consistency of TTS labels, but the primary metric is partly enforced by the dictionary constraint rather than learned.