# Feature reinforcement with word embedding and parsing information in neural TTS

arXiv: https://arxiv.org/abs/1901.00707 · HTML: https://mlsanity.com/paper/1901.00707/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jan 2019.

## Built on by (most cited first, 4 of 4)

- [PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS](https://mlsanity.com/paper/2103.15060/) (2021)
- [The Ethical Implications of Generative Audio Models: A Systematic Literature Review](https://mlsanity.com/paper/2307.05527/) (2023)
- [DiffEditor: Enhancing Speech Editing with Semantic Enrichment and Acoustic Consistency](https://mlsanity.com/paper/2409.12992/) (2024)
- [Investigation of Japanese PnG BERT language model in text-to-speech synthesis for pitch accent language](https://mlsanity.com/paper/2212.08321/) (2022)

## Abstract (arXiv)

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.