论文标题
一种新颖的中国方言TTS前端，具有非自动回归神经机器翻译
A Novel Chinese Dialect TTS Frontend with Non-Autoregressive Neural Machine Translation
论文作者
论文摘要
中文方言是中文的不同变化，可以被视为与普通话同一语言家族中的不同语言。尽管他们都使用汉字，但发音，语法和习语可能会有很大差异，甚至本地扬声器也可能发现很难输入正确的书面方言。此外，使用普通话文本作为文本到语音输入将产生自然性差的语音。在本文中，我们提出了一种新型的中国方言TTS前端，并带有翻译模块，该模块将普通话文本转换为辩证表达式，以提高合成语音的清晰度和自然性。对于翻译任务，提出了一种具有各种技巧的非自动性神经机器翻译模型。这是将翻译与TTS Frontend合并的第一项已知作品。广东话的实验表明，提出的模型可改善2.56 BLEU，而TTS则用普通话输入提高了0.27 MOS。
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.
