Xiang Yin

Xiang Yin

Auto-generated profile, based on publicly available information

Xiang Yin

Bytedance AI-Lab Shanghai Jiaotong University

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2016 in Speech Communication
Verified
Journal Article
Closed access
XYXiang Yin
Xiang Yin
MLMing Lei
Ming Lei
YQYao Qian
Yao Qian
FSFrank K. Soong
Frank K. Soong
LHLei He
Lei He
LDLi-Rong Dai
Li-Rong Dai

11 November 2019 in arXiv
Verified
Preprint
Open access
PDF file
JPJunjie Pan
Junjie Pan
XYXiang Yin
Xiang Yin
ZZZhiling Zhang
Zhiling Zhang
Shichao LiuShichao Liu
Shichao Liu
Yang ZhangYang Zhang
Yang Zhang
YWYuxuan Wang
Yuxuan Wang
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).