papers AI Learner
The Github is limit! Click to go to the new site.

Feature reinforcement with word embedding and parsing information in neural TTS

2019-01-03
Huaiping Ming, Lei He, Haohan Guo, Frank Soong

Abstract

In this paper, we propose a feature reinforcement method under the sequence-to-sequence neural text-to-speech (TTS) synthesis framework. The proposed method utilizes the multiple input encoder to take three levels of text information, i.e., phoneme sequence, pre-trained word embedding, and grammatical structure of sentences from parser as the input feature for the neural TTS system. The added word and sentence level information can be viewed as the feature based pre-training strategy, which clearly enhances the model generalization ability. The proposed method not only improves the system robustness significantly but also improves the synthesized speech to near recording quality in our experiments for out-of-domain text.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1901.00707

PDF

http://arxiv.org/pdf/1901.00707


Comments

Content