Search Results
Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
dathudeptrai/TensorflowTTS
•
•
This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text.
Ranked #2 on
Speech Synthesis
on North American English
FastSpeech: Fast,Robustand Controllable Text-to-Speech
dathudeptrai/TensorflowTTS
•
•
Compared with traditional concatenative and statistical parametric approaches, neural network based end-to-end models suffer from slow inference speed, and the synthesized speech is usually not robust (i. e., some words are skipped or repeated) and lack of controllability (voice speed or prosody control).
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
dathudeptrai/TensorflowTTS
•
•
ICLR 2021
In this paper, we propose FastSpeech 2, which addresses the issues in FastSpeech and better solves the one-to-many mapping problem in TTS by 1) directly training the model with ground-truth target instead of the simplified output from teacher, and 2) introducing more variation information of speech (e. g., pitch, energy and more accurate duration) as conditional inputs.
Ranked #6 on
Text-To-Speech Synthesis
on LJSpeech
(using extra training data)
MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
dathudeptrai/TensorflowTTS
•
•
NeurIPS 2019
In this paper, we show that it is possible to train GANs reliably to generate high quality coherent waveforms by introducing a set of architectural changes and simple training techniques.
FastSpeech: Fast, Robust and Controllable Text to Speech
dathudeptrai/TensorflowTTS
•
•
NeurIPS 2019
In this work, we propose a novel feed-forward network based on Transformer to generate mel-spectrogram in parallel for TTS.
Ranked #10 on
Text-To-Speech Synthesis
on LJSpeech
(using extra training data)
