FlashSpeech: Efficient Zero-Shot Speech Synthesis

TL;DR

FlashSpeech is a large-scale zero-shot speech synthesis system with approximately 5% of the inference time compared with previous work that 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.

Abstract

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/.

Figures (5)

• Figure 1: The inference time comparisons of different zero-shot speech synthesis systems using the real-time factor (RTF).
• Figure 2: Overall architecture of FlashSpeech. Our FlashSpeech consists of a codec encoder/decoder and a latent consistency model conditioned on feature from a phoneme and $\mathbf{z}_{prompt}$ encoder and a prosody generator. A discriminator is used during training.
• Figure 3: An illustration of adversarial consistency training.
• Figure 4: An illustration of prosody generator.
• Figure 5: User preference study. We compare the audio quality and speaker similarity of FlashSpeech against baselines with their official demo.