DDTSE: Discriminative Diffusion Model for Target Speech Extraction
This addresses the problem of slow inference in diffusion models for speech extraction, offering a practical improvement for audio processing applications.
The paper tackles target speech extraction in multi-speaker noisy conditions by introducing DDTSE, a discriminative diffusion model that achieves higher perceptual quality and accelerates inference by 3 times compared to conventional diffusion models.
Diffusion models have gained attention in speech enhancement tasks, providing an alternative to conventional discriminative methods. However, research on target speech extraction under multi-speaker noisy conditions remains relatively unexplored. Moreover, the superior quality of diffusion methods typically comes at the cost of slower inference speed. In this paper, we introduce the Discriminative Diffusion model for Target Speech Extraction (DDTSE). We apply the same forward process as diffusion models and utilize the reconstruction loss similar to discriminative methods. Furthermore, we devise a two-stage training strategy to emulate the inference process during model training. DDTSE not only works as a standalone system, but also can further improve the performance of discriminative models without additional retraining. Experimental results demonstrate that DDTSE not only achieves higher perceptual quality but also accelerates the inference process by 3 times compared to the conventional diffusion model.