利用一致性保持损失与感知对比度拉伸提升基于SSL的语音增强
Exploiting Consistency-Preserving Loss and Perceptual Contrast Stretching to Boost SSL-based Speech Enhancement
AI总结：
针对基于SSL的语音增强性能不足问题，提出结合Transformer掩码生成、一致性保持损失和PCS的Conformer增强框架，在VoiceBank-DEMAND上达到3.54的SOTA PESQ。
摘要：
自监督表示学习（SSL）已在多项下游语音任务上取得SOTA结果，但基于SSL的语音增强（SE）方案仍然落后。为解决这一问题，本文利用三个主要思路：（i）基于Transformer的掩码生成，（ii）一致性保持损失，以及（iii）感知对比度拉伸（PCS）。具体而言，引入借助注意力机制的conformer层，以有效建模帧级表示并获得用于SE的理想比率掩码（IRM）。此外，本文在损失函数中加入一致性，该函数处理输入以解释从频谱图重建信号所产生的不一致效应。最后，采用PCS根据感知重要性提升输入和目标特征的对比度。在VoiceBank-DEMAND任务上评估时，所提方案在多项客观指标测试中优于以往基于SSL的SE方案，并取得3.54的SOTA PESQ分数。
英文摘要：
Self-supervised representation learning (SSL) has attained SOTA results on several downstream speech tasks, but SSL-based speech enhancement (SE) solutions still lag behind. To address this issue, we exploit three main ideas: (i) Transformer-based masking generation, (ii) consistency-preserving loss, and (iii) perceptual contrast stretching (PCS). In detail, conformer layers, leveraging an attention mechanism, are introduced to effectively model frame-level representations and obtain the Ideal Ratio Mask (IRM) for SE. Moreover, we incorporate consistency in the loss function, which processes the input to account for the inconsistency effects of signal reconstruction from the spectrogram. Finally, PCS is employed to improve the contrast of input and target features according to perceptual importance. Evaluated on the VoiceBank-DEMAND task, the proposed solution outperforms previously SSL-based SE solutions when tested on several objective metrics, attaining a SOTA PESQ score of 3.54.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
