SignRecGAN trains on separate sign and speech datasets via adversarial and reconstruction objectives to inject sign-derived prosody into TTS output using the S2PFormer model.
CoRRabs/1510.01949(2015), http://arxiv.org/abs/1510
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Sign-to-Speech Prosody Transfer via Sign Reconstruction-based GAN
SignRecGAN trains on separate sign and speech datasets via adversarial and reconstruction objectives to inject sign-derived prosody into TTS output using the S2PFormer model.