An end-to-end Korean singing voice synthesizer with phonetic enhancement masking, local conditioning, and conditional adversarial training outperforms its ablated versions in listening tests.
We showed that using text information to model the phonetic enhancement mask actually worked, and produced more accurate pronunciation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adversarially Trained End-to-end Korean Singing Voice Synthesis System
An end-to-end Korean singing voice synthesizer with phonetic enhancement masking, local conditioning, and conditional adversarial training outperforms its ablated versions in listening tests.