Automatic prosody prediction for Chinese speech synthesis using BLSTM-RNN and embedding features

By Chuang Ding, Lei Xie, Jie Yan, Weini Zhang, Yang Liu. 2015

48 citations recorded by the source corpus.

Prosody affects the naturalness and intelligibility of speech. However, automatic prosody prediction from text for Chinese speech synthesis is still a great challenge and the traditional conditional random fields (CRF) based method always heavily relies on feature engineering. In this paper, we propose to use neural networks to predict prosodic boundary labels directly from Chinese characters without any feature engineering. Experimental results show that stacking feed-forward and bidirectional long short-term memory (BLSTM) recurrent network layers achieves superior performance over the CRF-based method. The embedding features learned from raw text further enhance the performance.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Frank K. Soong
5. Sheng Zhao
6. Lei Xie
7. Changhao Shan
8. Yi Ren

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, methodology): “For Chinese speech synthesis, the typical prosody boundary labels consist of prosodic word (PW), prosodic phrase (PPH) and intonational phrase (IPH), which can construct a three-layer hierarchical prosody tree [50, 322, 62].”
• A bi-directional LSTM approach for polyphone disambiguation in Mandarin Chinese (2016, background): “RNNs, especially those networks with LSTM cells, have recently produced promising results on a variety of tasks including language modeling [19] [20], speech recognition [21] and other sequential labelling tasks [14, 15, 16, 17, 22, 23, 24].”