基于流的语音转换改进发音的跨语言文本到语音合成
Cross-lingual Text-To-Speech with Flow-based Voice Conversion for Improved Pronunciation
AI总结：
本文提出基于非注意力Tacotron与归一化流网络的端到端跨语言TTS方法，通过同一模型实现TTS与语音转换，在低资源场景下改善目标语言发音并取得优于基线的效果。
摘要：
本文提出了一种端到端跨语言文本到语音合成（TTS）方法，旨在无论原始说话人使用何种语言，都保留目标语言的发音。所用模型基于非注意力机制的Tacotron架构，其中解码器被替换为以说话人身份为条件的归一化流网络，由于语言内容与说话人身份的内在解耦，同一模型既能执行TTS也能执行语音转换（VC）。在跨语言场景下，首先由目标语言的母语说话人生成声学特征，然后由同一模型应用语音转换，将这些特征转换为目标说话人的声音。我们通过客观和主观评估验证，与基线跨语言合成相比，本方法能够带来收益。通过纳入平均语音时长为7.5分钟的说话人，我们还展示了在低资源场景下的积极结果。
英文摘要：
This paper presents a method for end-to-end cross-lingual text-to-speech (TTS) which aims to preserve the target language's pronunciation regardless of the original speaker's language. The model used is based on a non-attentive Tacotron architecture, where the decoder has been replaced with a normalizing flow network conditioned on the speaker identity, allowing both TTS and voice conversion (VC) to be performed by the same model due to the inherent linguistic content and speaker identity disentanglement. When used in a cross-lingual setting, acoustic features are initially produced with a native speaker of the target language and then voice conversion is applied by the same model in order to convert these features to the target speaker's voice. We verify through objective and subjective evaluations that our method can have benefits compared to baseline cross-lingual synthesis. By including speakers averaging 7.5 minutes of speech, we also present positive results on low-resource scenarios.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
