TY - JOUR
AU1 - Zhang, Yang
AU2 - Deng, Liqun
AU3 - Wang, Yasheng
AB - Abstract: The front-end module in a typical Mandarin text-to-speech system (TTS) is composed of a long pipeline of text processing components, which requires extensive efforts to build and is prone to large accumulative model size and cascade errors. In this paper, a pre-trained language model (PLM) based model is proposed to simultaneously tackle the two most important tasks in TTS front-end, i.e., prosodic structure prediction (PSP) and grapheme-to-phoneme (G2P) conversion. We use a pre-trained Chinese BERT[1] as the text encoder and employ multi-task learning technique to adapt it to the two TTS front-end tasks. Then, the BERT encoder is distilled into a smaller model by employing a knowledge distillation technique called TinyBERT[2], making the whole model size 25% of that of benchmark pipeline models while maintaining competitive performance on both tasks. With the proposed the methods, we are able to run the whole TTS front-end module in a light and unified manner, which is more friendly to deployment on mobile devices.
TI - Unified Mandarin TTS Front-end Based on Distilled BERT Model
JF - Computing Research Repository
DA - 2020-12-31
UR - https://www.deepdyve.com/lp/arxiv-cornell-university/unified-mandarin-tts-front-end-based-on-distilled-bert-model-Ix5RYGrFGc
VL - 2021
IS - 2012
DP - DeepDyve
ER -