This paper integrates a classic mel-cepstral synthesis filter into a mod...
We propose PeriodNet, a non-autoregressive (non-AR) waveform generation ...
Nowadays vast amounts of speech data are recorded from low-quality recor...
The present paper describes singing voice synthesis based on convolution...
Neural waveform models such as WaveNet have demonstrated better performa...
Recently, we proposed short-time Fourier transform (STFT)-based loss
fun...
Speakers usually adjust their way of talking in noisy environments
invol...
End-to-end speech synthesis is a promising approach that directly conver...
Neural waveform models such as the WaveNet are used in many recent
text-...
This paper proposes a new loss using short-time Fourier transform (STFT)...
Recent neural networks such as WaveNet and sampleRNN that learn directly...
Recent advances in speech synthesis suggest that limitations such as the...
This paper describes a novel energy-based probabilistic distribution tha...