Search Results for author:
Found 6 papers, 3 papers with code
FastFit: Towards Real-Time Iterative Neural Vocoder by Replacing U-Net Encoder With Multiple STFTs
This paper presents FastFit, a novel neural vocoder architecture that replaces the U-Net encoder with multiple short-time Fourier transforms (STFTs) to achieve faster generation rates without sacrificing sample quality.
JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech
In neural text-to-speech (TTS), two-stage system or a cascade of separately learned models have shown synthesis quality close to human speech.
UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation
Using full-band mel-spectrograms as input, we expect to generate high-resolution signals by adding a discriminator that employs spectrograms of multiple resolutions as the input.
Universal MelGAN: A Robust Neural Vocoder for High-Fidelity Waveform Generation in Multiple Domains
To preserve sound quality when the MelGAN-based structure is trained with a dataset of hundreds of speakers, we added multi-resolution spectrogram discriminators to sharpen the spectral resolution of the generated waveforms.
JDI-T: Jointly trained Duration Informed Transformer for Text-To-Speech without Explicit Alignment
We propose Jointly trained Duration Informed Transformer (JDI-T), a feed-forward Transformer with a duration predictor jointly trained without explicit alignments in order to generate an acoustic feature sequence from an input text.
Convolutional Attention-based Seq2Seq Neural Network for End-to-End ASR
This thesis introduces the sequence to sequence model with Luong's attention mechanism for end-to-end ASR.
