TTS Models

Neural TTS Models

Tacotron

• Submitted: Mar 29, 2017
• Paper: https://arxiv.org/pdf/1703.10135.pdf
• Github: https://github.com/keithito/tacotron (Not the official implementation but is the once cited the most)

Tacotron2

• Submitted: Dec 16, 2017
• Paper: https://arxiv.org/pdf/1712.05884.pdf
• Github: https://github.com/NVIDIA/tacotron2

Transformer TTS

• Submitted: Sept 19, 2018
• Paper: https://arxiv.org/pdf/1809.08895.pdf
• Github: N/A

Flowtron

• Submitted: May 12, 2020
• Paper: https://arxiv.org/pdf/2005.05957.pdf
• Github: https://github.com/NVIDIA/flowtron

FastSpeech2

• Submitted: Jun 8, 2020
• Paper: https://arxiv.org/pdf/2006.04558.pdf
• Github: https://github.com/ming024/FastSpeech2 (Not the official implementation but is the once cited the most)

FastPitch

• Submitted: Jun 11, 2020
• Paper: https://arxiv.org/pdf/2006.06873.pdf
• Github: https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/SpeechSynthesis/FastPitch

TalkNet (1/2)

• Submitted: May 12, 2020/ Apr 16, 2021
• Paper: https://arxiv.org/pdf/2005.05514.pdf / https://arxiv.org/pdf/2104.08189.pdf
• Github: https://github.com/NVIDIA/NeMo

GlowTTS

• Submitted: May 22, 2020
• Paper: https://arxiv.org/pdf/2005.11129v1.pdf
• Github: https://github.com/jaywalnut310/glow-tts

GradTTS (Diffusion TTS)

• Submitted: May 13, 2021
• Paper: https://arxiv.org/pdf/2105.06337.pdf
• Github: https://github.com/huawei-noah/Speech-Backbones/tree/main/Grad-TTS

RadTTS

• Submitted: Aug 18, 2021
• Paper: https://openreview.net/pdf?id=0NQwnnwAORi
• Github: https://github.com/NVIDIA/radtts

Neural-HMMs

• Submitted: 30 Aug 2021
• Paper: https://arxiv.org/abs/2108.13320
• GitHub: https://github.com/shivammehta25/Neural-HMM

OverFlow

• Submitted: 13 Nov 2022
• Paper: https://arxiv.org/abs/2211.06892
• GitHub: https://github.com/shivammehta25/OverFlow

Matcha-TTS

• Submitted: 6 Sep 2023
• Paper: https://arxiv.org/abs/2309.03199
• GitHub: https://github.com/shivammehta25/Matcha-TTS

Vocoders (Mel-spec to audio)

WaveNet

• Submitted: Sept 12, 2016
• Paper: https://arxiv.org/pdf/1609.03499v2.pdf
• Github: N/A

WaveGlow

• Submitted: Oct 31, 2018
• Paper: https://arxiv.org/pdf/1811.00002.pdf
• Github: https://github.com/NVIDIA/waveglow

HiFiGAN

• Submitted: Oct 12, 2020
• Paper: https://arxiv.org/pdf/2010.05646.pdf
• Github: https://github.com/jik876/hifi-gan

MixerTTS

• Submitted: Oct 7, 2021
• Paper: https://arxiv.org/pdf/2110.03584.pdf
• Github: https://github.com/NVIDIA/NeMo

VITS

• Submitted: Jun 11, 2021
• Paper: https://arxiv.org/pdf/2106.06103.pdf
• Github: https://github.com/jaywalnut310/vits

STYLER

• Submitted: Mar 17, 2021
• Paper: https://arxiv.org/pdf/2103.09474.pdf
• Github: https://github.com/keonlee9420/STYLER

TorToiseTTS

• Submitted: N/A
• Paper: N/A
• Github: https://github.com/neonbjb/tortoise-tts

DiffTTS (DiffSinger)

• Submitted: Apr 3, 2021
• Paper: https://arxiv.org/pdf/2104.01409v1.pdf
• Github: https://github.com/keonlee9420/DiffSinger

Uncategorised / Unevaluated

eSpeak

• Submitted: N/A
• Paper: https://arxiv.org/abs/2305.15255.pdf
• Github: https://github.com/espeak-ng/espeak-ng

CMU Flite TTS

• Submitted: N/A
• Paper: https://www.cs.cmu.edu/~awb/Papers/ISCA01/flite/flite.html
• Github: https://github.com/festvox/flite

MaryTTS

• Submitted: N/A
• Paper: https://arxiv.org/abs/1712.04787.pdf
• Github: https://github.com/marytts/marytts

Mimic 3

• Note: Don’t get mixed with MIMIC-III, a medical database.
• Submitted: N/A
• Paper: N/A
• Github: https://github.com/MycroftAI/mimic3

MBROLA

• Submitted: N/A
• Paper: https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=7b1fdadf05b8f968a5b361f6f82852ade62c8010
• Github: https://github.com/numediart/MBROLA

SpeechT5

• Submitted: 14 Oct 2021
• Paper: https://arxiv.org/abs/2110.07205
• GitHub: https://github.com/microsoft/SpeechT5