Tacotron (/täkōˌträn/): An end-to-end speech synthesis system by Google

Publications

(March 2017) Tacotron: Towards End-to-End Speech Synthesis
(November 2017) Uncovering Latent Style Factors for Expressive Speech Synthesis
(December 2017) Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
(March 2018) Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron
(March 2018) Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
(June 2018) Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis
(July 2018) Predicting Expressive Speaking Style From Text in End-to-End Speech Synthesis
(August 2018) Semi-Supervised Training for Improving Data Efficiency in End-to-End Speech Synthesis
(October 2018) Hierarchical Generative Modeling for Controllable Speech Synthesis
(November 2018) Disentangling Correlated Speaker and Noise for Speech Synthesis via Data Augmentation and Adversarial Factorization
(April 2019) Parrotron: An End-to-End Speech-to-Speech Conversion Model and its Applications to Hearing-Impaired Speech and Speech Separation
(June 2019) Effective Use of Variational Embedding Capacity in Expressive End-to-End Speech Synthesis