Text-to-Speech Models

Edit

Audio • 12 methods

Methods

Add a Method

Method	Year	Papers
Tacotron Tacotron: Towards End-to-End Speech Synthesis	2017	62
Tacotron 2 Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions	2017	22
FastSpeech 2 FastSpeech 2: Fast and High-Quality End-to-End Text to Speech	2020	17
FastPitch FastPitch: Parallel Text-to-speech with Pitch Prediction	2020	8
ClariNet ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech	2018	7
Glow-TTS Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search	2020	6
ParaNet Non-Autoregressive Neural Text-to-Speech	2019	4
Deep Voice 3 Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning	2017	3
GAN-TTS High Fidelity Speech Synthesis with Adversarial Networks	2019	2
WaveTTS WaveTTS: Tacotron-based TTS with Joint Time-Frequency Domain Loss	2020	1
FastSpeech 2s FastSpeech 2: Fast and High-Quality End-to-End Text to Speech	2020	1