Chinese dialects are different variations of Chinese and can be considered as
different languages in the same language family with Mandarin. Though they all
use Chinese characters, the pronunciations, grammar and idioms can vary
significantly, and even local speakers may find it hard to input correct
written forms of dialect. Besides, using Mandarin text as text-to-speech inputs
would generate speech with poor naturalness. In this paper, we propose a novel
Chinese dialect TTS frontend with a translation module, which converts Mandarin
text into dialectic expressions to improve the intelligibility and naturalness
of synthesized speech. A non-autoregressive neural machine translation model
with various tricks is proposed for the translation task. It is the first known
work to incorporate translation with TTS frontend. Experiments on Cantonese
show the proposed model improves 2.56 BLEU and TTS improves 0.27 MOS with
Mandarin inputs.

本文提出了一种新颖的中文方言 TTS 前端和翻译模块，用于把标准普通话文本转化为方言表达以提高语音合成的可懂性和自然度。这是首个将翻译与 TTS 前端相结合的工作，使用非自回归神经机器翻译模型和多种技巧，且实验结果在粤语上显示出 2.56 BLEU 和 0.27 MOS 的性能提升。