Multi-View Attention Transfer for Efficient Speech Enhancement

Abstract

Recent deep learning models have achieved high performance in speech enhancement; however, it is still challenging to obtain a fast and low-complexity model without significant performance degradation. Previous knowledge distillation studies on speech enhancement could not solve this problem because their output distillation methods do not fit the speech enhancement task in some aspects. In this study, we propose multi-view attention transfer (MV-AT), a feature-based distillation, to obtain efficient speech enhancement models in the time domain. Based on the multi-view features extraction model, MV-AT transfers multi-view knowledge of the teacher network to the student network without additional parameters. The experimental results show that the proposed method consistently improved the performance of student models of various sizes on the Valentini and deep noise suppression (DNS) datasets. MANNER-S-8.1GF with our proposed method, a lightweight model for efficient deployment, achieved 15.4× and 4.71× fewer parameters and floating-point operations (FLOPs), respectively, compared to the baseline model with similar performance.

Sub-Band Knowledge Distillation Framework for Speech Enhancement

“…To alleviate this issue, [16] proposed aligning intermediate features, while [17] used attention maps to do so. The latter was applied in the context of SE in [18] using considerably large, non-causal student models intended for offline applications. In [19], the authors addressed the dimensionality mismatch problem for the causal SE models by using frame-level Similarity Preserving KD [20] (SPKD).…”