A Novel Chinese Dialect TTS Frontend with Non-Autoregressive Neural Machine Translation
This addresses the challenge of poor speech naturalness for dialect speakers when using Mandarin text inputs, though it is incremental as it builds on existing TTS and translation methods.
The paper tackles the problem of generating natural-sounding speech from Mandarin text for Chinese dialects by proposing a TTS frontend with a translation module, resulting in a 2.56 BLEU improvement in translation and a 0.27 MOS gain in speech quality for Cantonese.
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.