[tts] Multilingual Speech Synthesis 中英文混合语音合成

[yt605155624]

Input a sentence that contains both Chinese and English, and TTS outputs the corresponding audio and keeps the voice consistent

hello, 你好吗？I love you！

see: Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning

[lym0302]

中英混合语音合成部分代码已上传，后续会完善再合入 PaddleSpeech. https://github.com/lym0302/PaddleSpeech/tree/train_zh_en

[yt605155624]

PR:

• mix frontend: https://github.com/PaddlePaddle/PaddleSpeech/pull/2143
• the baseline of mix model: https://github.com/PaddlePaddle/PaddleSpeech/pull/2174
• cli support: https://github.com/PaddlePaddle/PaddleSpeech/pull/2203
• mix example: https://github.com/PaddlePaddle/PaddleSpeech/pull/2234
• update cli: https://github.com/PaddlePaddle/PaddleSpeech/pull/2249

[Lennon-cheng]

@lym0302 中英文语音合成，代码大概什么时候发出呀。或者中英文语音合成代码，除了 mix_frontend 不同外，还有哪些部分不同呀，谢谢

[yt605155624]

@Lennon-cheng 你好，paddlespeech 1.1 已经支持中英文混合了，欢迎试用！参考：

训练代码：

• https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/zh_en_tts/tts3

CLI：

• https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/demos/text_to_speech