VoiceCraft：野外环境下的零样本语音编辑与文本转语音
VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild
AI总结：
VoiceCraft是一种令牌填充神经编解码语言模型，通过Transformer解码器和令牌重排程序，在有声书、视频和播客等真实场景中同时实现了领先的语音编辑和零样本TTS性能，并发布了高难度数据集RealEdit。
摘要：
我们介绍了VoiceCraft，一种令牌填充神经编解码语言模型，它在有声书、互联网视频和播客上的语音编辑和零样本文本转语音（TTS）任务中均达到了最先进的性能。VoiceCraft采用Transformer解码器架构，并引入了一种令牌重排程序，该程序结合了因果掩码和延迟堆叠，以实现在现有序列内进行生成。在语音编辑任务上，VoiceCraft生成的编辑后语音在自然度方面经人类评估几乎与未编辑录音无法区分；对于零样本TTS，我们的模型优于先前的SotA模型，包括VALLE和流行的商业模型XTTS-v2。至关重要的是，这些模型在具有挑战性和现实性的数据集上进行了评估，这些数据集包含多样的口音、说话风格、录音条件以及背景噪音和音乐，并且与其他模型和真实录音相比，我们的模型表现始终良好。特别是对于语音编辑评估，我们引入了一个高质量、具有挑战性且现实的数据集，名为RealEdit。我们鼓励读者在https://jasonppy.github.io/VoiceCraft_web上试听演示。
英文摘要：
We introduce VoiceCraft, a token infilling neural codec language model, that achieves state-of-the-art performance on both speech editing and zero-shot text-to-speech (TTS) on audiobooks, internet videos, and podcasts. VoiceCraft employs a Transformer decoder architecture and introduces a token rearrangement procedure that combines causal masking and delayed stacking to enable generation within an existing sequence. On speech editing tasks, VoiceCraft produces edited speech that is nearly indistinguishable from unedited recordings in terms of naturalness, as evaluated by humans; for zero-shot TTS, our model outperforms prior SotA models including VALLE and the popular commercial model XTTS-v2. Crucially, the models are evaluated on challenging and realistic datasets, that consist of diverse accents, speaking styles, recording conditions, and background noise and music, and our model performs consistently well compared to other models and real recordings. In particular, for speech editing evaluation, we introduce a high quality, challenging, and realistic dataset named RealEdit. We encourage readers to listen to the demos at https://jasonppy.github.io/VoiceCraft_web.
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。
