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.
Specifically, we utilized the basic5000 subset along with its manually annotated TTS labels1
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 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.