Recent progress in large-scale zero-shot speech synthesis has been significantly advanced by language models and diffusion models. However, the generation process of both methods is slow and computationally intensive. Efficient speech synthesis using a lower computing budget to achieve quality on par with previous work remains a significant challenge. In this paper, we present FlashSpeech, a large-scale zero-shot speech synthesis system with approximately 5\% of the inference time compared with previous work. FlashSpeech is built on the latent consistency model and applies a novel adversarial consistency training approach that can train from scratch without the need for a pre-trained diffusion model as the teacher. Furthermore, a new prosody generator module enhances the diversity of prosody, making the rhythm of the speech sound more natural. The generation processes of FlashSpeech can be achieved efficiently with one or two sampling steps while maintaining high audio quality and high similarity to the audio prompt for zero-shot speech generation. Our experimental results demonstrate the superior performance of FlashSpeech. Notably, FlashSpeech can be about 20 times faster than other zero-shot speech synthesis systems while maintaining comparable performance in terms of voice quality and similarity. Furthermore, FlashSpeech demonstrates its versatility by efficiently performing tasks like voice conversion, speech editing, and diverse speech sampling. Audio samples can be found in https://flashspeech.github.io/.

翻译：近年来，大规模零样本语音合成技术因语言模型和扩散模型的推动取得了显著进展。然而，这两种方法的生成过程速度较慢且计算强度高。如何在更低的计算预算下实现与先前工作质量相当的语音合成效率仍是一项重大挑战。本文提出FlashSpeech——一种大规模零样本语音合成系统，其推理时间约为先前工作的5%。FlashSpeech基于潜在一致性模型构建，并采用一种新颖的对抗性一致性训练方法，该方法无需预训练扩散模型作为教师即可从零开始训练。此外，新增的韵律生成器模块增强了韵律多样性，使语音节奏更自然。FlashSpeech的生成过程仅需一至两步采样即可高效完成，同时保持高音频质量与对音频提示的高度相似性。实验结果表明，FlashSpeech具有卓越性能。值得注意的是，FlashSpeech的速度可比其他零样本语音合成系统快约20倍，同时在音质与相似性方面保持可比性能。此外，FlashSpeech还展现了其在语音转换、语音编辑与多样化语音采样等任务中的高效通用性。音频示例见https://flashspeech.github.io/。