Links

• ​Deepvoice3 PyTorch - PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models.

• ​WaveNet vocoder - Can generate high quality raw speech samples conditioned on linguistic or acoustic features.

• ​Papercup - Translate your content into other languages with a voice that sounds like yours.

• ​WaveNet implementation in Keras​

• ​nv-wavenet - CUDA reference implementation of autoregressive WaveNet inference.

• ​PyTorch implementation of Tacotron speech synthesis model​

• ​Yet another WaveNet implementation in PyTorch​

• ​Flowtron - Auto-regressive flow-based generative network for text to speech synthesis.

• ​A highly efficient, real-time text-to-speech system deployed on CPUs (2020) (HN)

• ​Sonatic - Emotionally Expressive Text to Speech.

• ​GAN-based Mel-Spectrogram Inversion Network for Text-to-Speech Synthesis​

• ​Ask HN: My wife might lose the ability to speak in 3 weeks – how to prepare? (2020)​

• ​DiffWave - Fast, high-quality neural vocoder and waveform synthesizer.

• ​Voice Conversion with Non-Parallel Data​

• ​Speech Synthesis Papers​

• ​VoiceFilter - Unofficial PyTorch implementation of Google AI's VoiceFilter system. (Web)

• ​ForwardTacotron - Generating speech in a single forward pass without any attention. (Web)

• ​HiFi-GAN - Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis.

• ​Parakeet - Text-to-speech toolKIT (supporting WaveFlow, ClariNet, WaveNet, Deep Voice 3, Transformer TTS and FastSpeech).

• ​pyttsx3 - Offline Text To Speech synthesis for python.

• ​SOVA TTS - Speech syntthesis solution based on Tacotron 2 architecture.

• ​eSpeak NG - Open source speech synthesizer that supports more than hundred languages and accents.

• ​PRiSM SampleRNN - Neural sound synthesis with TensorFlow 2.

• ​Flite - Small fast portable speech synthesis system.

• ​FastSpeech 2: Fast and High-Quality End-to-End Text to Speech (2020) (Code)

• ​Neural Granular Sound Synthesis (Code)

• ​CLEESE - Combinatorial Expressive Speech Engine.

• ​LVCNet: Efficient Condition-Dependent Modeling Network for Waveform Generation​

• ​LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search (2021) (Code)