KALL-E：基于下一分布预测的自回归语音合成
KALL-E:Autoregressive Speech Synthesis with Next-Distribution Prediction
AI总结：
提出KALL-E，一种基于下一分布预测的自回归TTS模型，利用Flow-VAE提取连续语音表示并由AR Transformer预测分布，无需扩散组件，实现了高质量语音合成及单样本说话人适应。
摘要：
我们提出了KALL-E，一种用于文本到语音（TTS）合成的全新自回归（AR）语言模型，它通过预测连续语音帧的下一分布来运行。与现有方法不同，KALL-E直接对基于文本条件的连续语音分布进行建模，消除了对任何基于扩散的组件的需求。具体而言，我们利用Flow-VAE从波形中提取连续的潜在语音表示，而不是依赖离散语音标记。随后训练单个AR Transformer根据文本预测这些连续语音分布，并将优化Kullback-Leibler散度损失作为其目标。实验结果表明，KALL-E实现了卓越的语音合成质量，甚至能够仅从单个样本适应目标说话人。重要的是，KALL-E为在TTS中利用连续语音表示提供了一种更直接有效的方法。
英文摘要：
We introduce KALL-E, a novel autoregressive (AR) language model for text-to-speech (TTS) synthesis that operates by predicting the next distribution of continuous speech frames. Unlike existing methods, KALL-E directly models the continuous speech distribution conditioned on text, eliminating the need for any diffusion-based components. Specifically, we utilize a Flow-VAE to extract a continuous latent speech representation from waveforms, instead of relying on discrete speech tokens. A single AR Transformer is then trained to predict these continuous speech distributions from text, optimizing a Kullback-Leibler divergence loss as its objective. Experimental results demonstrate that KALL-E achieves superior speech synthesis quality and can even adapt to a target speaker from just a single sample. Importantly, KALL-E provides a more direct and effective approach for utilizing continuous speech representations in TTS.
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。
