A text-to-speech synthesis system typically consists of multiple stages, such as a text analysis frontend, an acoustic model and an audio synthesis module. Building these components often requires extensive domain expertise and may contain brittle design choices. In this paper, we present Tacotron, an end-to-end generative text-to-speech model that synthesizes speech directly from characters. Given <text, audio> pairs, the model can be trained completely from scratch with random initialization. We present several key techniques to make the sequence-to-sequence framework perform well for this challenging task. Tacotron achieves a 3.82 subjective 5-scale mean opinion score on US English, outperforming a production parametric system in terms of naturalness. In addition, since Tacotron generates speech at the frame level, it’s substantially faster than sample-level autoregressive methods.
Cite as: Wang, Y., Skerry-Ryan, R.J., Stanton, D., Wu, Y., Weiss, R.J., Jaitly, N., Yang, Z., Xiao, Y., Chen, Z., Bengio, S., Le, Q., Agiomyrgiannakis, Y., Clark, R., Saurous, R.A. (2017) Tacotron: Towards End-to-End Speech Synthesis. Proc. Interspeech 2017, 4006-4010, doi: 10.21437/Interspeech.2017-1452
@inproceedings{wang17n_interspeech,
author={Yuxuan Wang and R.J. Skerry-Ryan and Daisy Stanton and Yonghui Wu and Ron J. Weiss and Navdeep Jaitly and Zongheng Yang and Ying Xiao and Zhifeng Chen and Samy Bengio and Quoc Le and Yannis Agiomyrgiannakis and Rob Clark and Rif A. Saurous},
title={{Tacotron: Towards End-to-End Speech Synthesis}},
year=2017,
booktitle={Proc. Interspeech 2017},
pages={4006--4010},
doi={10.21437/Interspeech.2017-1452}
}