Speech Synthesis
Speech synthesis is the task of generating speech from text.
Please note that the state-of-the-art tables here are not really comparable between studies - as they use mean opinion score as a metric and collect different samples from Amazon Mechnical Turk.
State-of-the-art leaderboards
| Trend | Dataset | Best Method | Paper title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
||||||
|
Greatest papers with code
WaveNet: A Generative Model for Raw Audio
• buriburisuri/speech-to-text-wavenet
• 
This paper introduces WaveNet, a deep neural network for generating raw audio waveforms.
SOTA for Speech Synthesis on Mandarin Chinese
Tacotron: Towards End-to-End Speech Synthesis
A text-to-speech synthesis system typically consists of multiple stages, such as a text analysis frontend, an acoustic model and an audio synthesis module.
#4 best model for
Speech Synthesis
on North American English
WaveGlow: A Flow-based Generative Network for Speech Synthesis
• NVIDIA/waveglow
• 
In this paper we propose WaveGlow: a flow-based network capable of generating high quality speech from mel-spectrograms.
Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning
ICLR 2018
• r9y9/deepvoice3_pytorch
•
We present Deep Voice 3, a fully-convolutional attention-based neural text-to-speech (TTS) system.
Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text.
Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2Seq
We present OpenSeq2Seq - a TensorFlow-based toolkit for training sequence-to-sequence models that features distributed and mixed-precision training.
Deep Voice: Real-time Neural Text-to-Speech
We present Deep Voice, a production-quality text-to-speech system constructed entirely from deep neural networks.
A Real-Time Wideband Neural Vocoder at 1.6 kb/s Using LPCNet
We demonstrate that LPCNet operating at 1. 6 kb/s achieves significantly higher quality than MELP and that uncompressed LPCNet can exceed the quality of a waveform codec operating at low bitrate.
LPCNet: Improving Neural Speech Synthesis Through Linear Prediction
We demonstrate that LPCNet can achieve significantly higher quality than WaveRNN for the same network size and that high quality LPCNet speech synthesis is achievable with a complexity under 3 GFLOPS.
Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks
• r9y9/gantts
•
In the proposed framework incorporating the GANs, the discriminator is trained to distinguish natural and generated speech parameters, while the acoustic models are trained to minimize the weighted sum of the conventional minimum generation loss and an adversarial loss for deceiving the discriminator.