【2021.07.27-30概覽】arxiv每日語音合成相關更新
作者:由 LabmemZhouyx 發表于 書法時間:2021-08-02
1】Facetron: Multi-speaker Face-to-Speech Model based on Cross-modal Latent Representations
延世大學
論文地址:
https://
arxiv。org/abs/2107。1200
3
2】
Beyond Voice Identity Conversion: Manipulating Voice Attributes by Adversarial Learning of Structured Disentangled Representations
索邦大學
論文地址:
https://
arxiv。org/abs/2107。1234
6
3】
Cross-speaker Style Transfer with Prosody Bottleneck in Neural Speech Synthesis(Interspeech 2021)
微軟
論文地址:
https://
arxiv。org/abs/2107。1256
2