Xiang Yin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Xiang Yin has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Frank K. Soong
Microsoft Research Asia, Beijing, China
1 shared publication - Junjie Pan
Bytedance AI-Lab Shanghai Jiaotong University
1 shared publication - Lei He
Microsoft Beijing China
1 shared publication - Li-Rong Dai
University of Science and Technology of China, Hefei, China
1 shared publication - Ming Lei
Microsoft, Beijing, China
1 shared publication - Shichao Liu
Department of Electronics, Carleton University, Ottawa, ON, Canada
1 shared publication
Latest Publications
- Open Access
A unified sequence-to-sequence front-end model for Mandarin text-to-speech synthesis
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).
Open AccessA unified sequence-to-sequence front-end model for Mandarin text-to-speech synthesis
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).
- 1 February 2016
- Published by Elsevier in Speech Communication
- Vol. 76, 82-92
Modeling F0 trajectories in hierarchically structured deep neural networks
- 1 February 2016
- Published by Elsevier in Speech Communication
- Vol. 76, 82-92
Modeling F0 trajectories in hierarchically structured deep neural networks