Talking face generation has been extensively investigated owing to its w...
This paper proposes singing voice synthesis (SVS) based on frame-level
s...
This paper proposes a novel sequence-to-sequence (seq2seq) model with a
...
This paper integrates a classic mel-cepstral synthesis filter into a mod...
The recent text-to-speech (TTS) has achieved quality comparable to that ...
This paper presents Sinsy, a deep neural network (DNN)-based singing voi...
We propose PeriodNet, a non-autoregressive (non-AR) waveform generation ...
This paper proposes a hierarchical generative model with a multi-grained...