| Title | A Universal Bert-Based Front-End Model for Mandarin Text-To-Speech Synthesis |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Bai, Zilong, Hu, Beibei |
| Conference Name | ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |
| Date Published | jun |
| Keywords | Acoustics, BERT, compositionality, Conferences, expandability, feature extraction, front-end, multi-task learning, Predictive models, pubcrawl, Resiliency, Signal processing, speech processing, Task Analysis, text-to-speech |
| Abstract | The front-end text processing module is considered as an essential part that influences the intelligibility and naturalness of a Mandarin text-to-speech system significantly. For commercial text-to-speech systems, the Mandarin front-end should meet the requirements of high accuracy and low time latency while also ensuring maintainability. In this paper, we propose a universal BERT-based model that can be used for various tasks in the Mandarin front-end without changing its architecture. The feature extractor and classifiers in the model are shared for several sub-tasks, which improves the expandability and maintainability. We trained and evaluated the model with polyphone disambiguation, text normalization, and prosodic boundary prediction for single task modules and multi-task learning. Results show that, the model maintains high performance for single task modules and shows higher accuracy and lower time latency for multi-task modules, indicating that the proposed universal front-end model is promising as a maintainable Mandarin front-end for commercial applications. |
| DOI | 10.1109/ICASSP39728.2021.9414935 |
| Citation Key | bai_universal_2021 |
A Universal Bert-Based Front-End Model for Mandarin Text-To-Speech Synthesis