Speech Synthesis

Here we include the list of available datasets as well as important publications on speech synthesis via artificial neural networks. |

Datasets

None

Publications

Architecture:Combined

Year:2018

Paper:Jia, Ye, et al. “Transfer learning from speaker verification to multispeaker text-to-speech synthesis.” Advances in neural information processing systems. 2018.

Architecture:modified Tacotron

Year:2018

Paper:Skerry-Ryan, R. J., et al. “Towards end-to-end prosody transfer for expressive speech synthesis with tacotron.” arXiv preprint arXiv:1803.09047 (2018).

Architecture:modified Wavenet

Year:2018

Paper:Shen, Jonathan, et al. “Natural tts synthesis by conditioning wavenet on mel spectrogram predictions.” 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2018.

Architecture:Tacotron

Year:2017

Paper:Wang, Yuxuan, et al. “Tacotron: A fully end-to-end text-to-speech synthesis model.” arXiv preprint (2017).

Architecture:Deep voice

Year:2017

Paper:Arik, Sercan O., et al. “Deep voice: Real-time neural text-to-speech.” arXiv preprint arXiv:1702.07825 (2017).

Architecture:WaveNet (based on PixelCNN)

Year:2016

Paper:Van Den Oord, Aäron, et al. “WaveNet: A generative model for raw audio.” SSW. 2016.

Architecture:LSTM-RNN

Year:2016

Paper:Zen, Heiga, et al. “Fast, compact, and high quality LSTM-RNN based statistical parametric speech synthesizers for mobile devices.” arXiv preprint arXiv:1606.06061 (2016).