SCALABLE AND EFFICIENT SPEECH ENHANCEMENT USING MODIFIED COLD DIFFUSION: A RESIDUAL LEARNING APPROACH

We introduce flexibility to the supervised learning-based speech enhancement framework to achieve scalable and efficient speech enhancement (SESE). To this end, SESE conducts a series of segmented speech enhancement inference routines, each of which incrementally improves the result of its preceding inference. The formulation is conceptually similar to cold diffusion, while we modify the sampling process so each step benefits from an easier milestone task rather than aggressively targeting the clean speech. In addition, the incremental enhancement steps are learned to recover the residual between the adjacent milestones, thus improving the overall enhancement performance. We show that the proposed method improves the baseline supervised model’s performance, while it necessitates fewer diffusion steps to achieve the comparable performance with the more complex cold diffusion-based counterpart. Furthermore, SESE’s scalability can be useful in applications where moderately suppressed non-speech interference is preferred to aggressive enhancement results, e.g., boosting dialog in movie soundtracks, speech enhancement on hearing aids, etc.