SlimSpeech: Lightweight and Efficient Text-to-Speech with Slim Rectified Flow
This work addresses efficiency and resource constraints in speech synthesis for applications requiring fast, low-cost deployment, though it is incremental as it builds upon existing rectified flow methods.
The paper tackles the problem of reducing model size and inference steps in text-to-speech synthesis by introducing SlimSpeech, a lightweight system based on rectified flow, which achieves comparable performance to larger models with significantly fewer parameters through one-step sampling.
Recently, flow matching based speech synthesis has significantly enhanced the quality of synthesized speech while reducing the number of inference steps. In this paper, we introduce SlimSpeech, a lightweight and efficient speech synthesis system based on rectified flow. We have built upon the existing speech synthesis method utilizing the rectified flow model, modifying its structure to reduce parameters and serve as a teacher model. By refining the reflow operation, we directly derive a smaller model with a more straight sampling trajectory from the larger model, while utilizing distillation techniques to further enhance the model performance. Experimental results demonstrate that our proposed method, with significantly reduced model parameters, achieves comparable performance to larger models through one-step sampling.