DC CoMix TTS：一种与Mixer协作的离散码端到端表现力TTS
DC CoMix TTS: An End-to-End Expressive TTS with Discrete Code Collaborated with Mixer
AI总结：
本文提出DC CoMix TTS，通过在参考编码器输入引入离散码并应用修改后的MLP-Mixer，实现轻量化的端到端韵律迁移TTS，有效缓解内容泄露问题并提升说话人无关韵律建模效果。
摘要：
尽管中性TTS取得了巨大成功，但内容泄露仍是一个挑战。本文提出一种新的输入表示和简单架构，以实现改进的韵律建模。受近期在TTS中使用离散码取得成功的启发，我们将离散码引入参考编码器的输入。具体而言，我们利用音频压缩模型中的vector quantizer，以利用其已训练的丰富声学信息。此外，我们将修改后的MLP-Mixer应用于参考编码器，使架构更轻量。因此，我们以端到端方式训练韵律迁移TTS。我们通过主观和客观评估证明了方法的有效性。实验表明，当离散码作为输入时，参考编码器能学习到更好的说话人无关韵律。此外，即使在输入更少参数的情况下，我们也获得了可比的结果。
英文摘要：
Despite the huge successes made in neutral TTS, content-leakage remains a challenge. In this paper, we propose a new input representation and simple architecture to achieve improved prosody modeling. Inspired by the recent success in the use of discrete code in TTS, we introduce discrete code to the input of the reference encoder. Specifically, we leverage the vector quantizer from the audio compression model to exploit the diverse acoustic information it has already been trained on. In addition, we apply the modified MLP-Mixer to the reference encoder, making the architecture lighter. As a result, we train the prosody transfer TTS in an end-to-end manner. We prove the effectiveness of our method through both subjective and objective evaluations. We demonstrate that the reference encoder learns better speaker-independent prosody when discrete code is utilized as input in the experiments. In addition, we obtain comparable results even when fewer parameters are inputted.
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。
