WaveTTS: Tacotron-based TTS with Joint Time-Frequency Domain Loss

2 Feb 2020 • Rui Liu • Berrak Sisman • Feilong Bao • Guanglai Gao • Haizhou Li

Tacotron-based text-to-speech (TTS) systems directly synthesize speech from text input. Such frameworks typically consist of a feature prediction network that maps character sequences to frequency-domain acoustic features, followed by a waveform reconstruction algorithm or a neural vocoder that generates the time-domain waveform from acoustic features... (read more)

PDF Abstract

Code

Add Remove Mark official

No code implementations yet. Submit your code now

Tasks

Add Remove

Results from the Paper

Edit

Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

METHOD	TYPE
Mixture of Logistic Distributions	Output Functions
Dilated Causal Convolution	Temporal Convolutions
WaveNet	Generative Audio Models
LSTM	Recurrent Neural Networks
Weight Decay	Regularization
Adam	Stochastic Optimization
Convolution	Convolutions
Griffin-Lim Algorithm	Phase Reconstruction
Location Sensitive Attention	Attention Mechanisms
Linear Layer	Feedforward Networks
BiLSTM	Bidirectional Recurrent Neural Networks
WaveTTS	Text-to-Speech Models

METHOD

TYPE

Mixture of Logistic Distributions