Phoneme boundary detection has been studied due to its central role in
v...
Various applications of voice synthesis have been developed independentl...
We present EdiTTS, an off-the-shelf speech editing methodology based on
...
Neural network training requires a large amount of computation and thus ...
Recent developments in deep learning have significantly improved the qua...
Although neural text-to-speech (TTS) models have attracted a lot of atte...
Photoplethysmogram (PPG) signal-based blood pressure (BP) estimation is ...
For multi-channel speech recognition, speech enhancement techniques such...
Recently, attention-based encoder-decoder (AED) models have shown
state-...
Flow-based generative models are composed of invertible transformations
...
In recent years, various flow-based generative models have been proposed...