A Unified Sequence-to-Sequence Front-End Model for Mandarin Text-to-Speech Synthesis

By Junjie Pan, Xiang Yin, Zhiling Zhang, Shichao Liu, Yang Zhang, Zejun Ma, Yuxuan Wang. 2019

28 citations recorded by the source corpus.

In Mandarin text-to-speech (TTS) system, the front-end text processing module significantly influences the intelligibility and naturalness of synthesized speech. Building a typical pipeline-based front-end which consists of multiple individual components requires extensive efforts. In this paper, we proposed a unified sequence-to-sequence front-end model for Mandarin TTS that converts raw texts to linguistic features directly. Compared to the pipeline-based front-end, our unified front-end can achieve comparable performance in polyphone disambiguation and prosody word prediction, and improve intonation phrase prediction by 0.0738 in F1 score. We also implemented the unified front-end with Tacotron and WaveRNN to build a Mandarin TTS system. The synthesized speech by that got a comparable MOS (4.38) with the pipeline-based front-end (4.37) and close to human recordings (4.49).

Subfields: Artificial Intelligence, Signal Processing

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. Dong Yu
6. Chao Weng
7. Jinyu Li
8. Xinyu Yang

In Signal Processing

1. Xu Tan
2. Tie-Yan Liu
3. Tao Qin
4. Frank K. Soong
5. Dong Yu
6. Chao Weng
7. Jinyu Li
8. Zhaoxi Mu

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, methodology): “TTS Text Analysis Char→Linguistic TN [310, 223, 430], G2P [403, 320, 321] Prosody Prediction [312, 137, 277, 251] Unified Model [252, 437] DeepVoice 1/2 [8, 84]”
• Review of end-to-end speech synthesis technology based on deep learning (2021, methodology): “A simple method to reduce exposure bias is scheduled sampling [13], in which acoustic feature frames of the current time step are predicted by using natural acoustic feature frames or those predicted by the previous time step with a certain probability [141, 155].”
• DurIAN: Duration Informed Attention Network for Speech Synthesis (2020, background): “Therefore, it is still more desirable to have a separate model for learning word and prosody boundaries from larger dataset [13, 14, 15] in tasks such as Mandarin speech synthesis.”