发表机构
Carl von Ossietzky University Oldenburg（卡尔·冯·奥西茨基奥尔登堡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出混合Transformer-U-Net架构U-PAST，在复频谱域通过自注意力建模解决CNNs间接捕获长时频依赖的局限，在多语料库多失配条件下表现优异，U-PAST-H性能最优且权衡性好。
AI 中文摘要
卷积神经网络（CNNs）在音频增强领域应用广泛且成效显著，但仅能通过连续卷积和池化间接捕获长时程时频依赖关系。本文提出U-PAST，一种混合Transformer-U-Net架构，在复频谱域通过自注意力依赖建模解决该局限。U-PAST对复短时傅里叶变换（STFT）表示进行分词，类似音频频谱图Transformer（AST）对幅度频谱图的分词操作，应用多层Transformer编码器，再通过U-Net风格解码器重建增强后的复频谱图。我们在DNS Challenge、VoiceBank-DEMAND和LibriMix语料库上，针对匹配、声学失配及双数据集失配条件，评估了4种参数规模在117万至240万之间的架构变体。U-PAST在声学失配条件下取得所有评估模型中最佳的尺度不变信号失真比（SI-SDR），在其余三种条件下仅比规模大得多的卷积与时域基线模型低0.26至0.63 dB SI-SDR，同时在数据集失配条件下实现最强的感知质量（DNSMOS）。评估的最大配置U-PAST-H（240万参数）始终是该系列中性能最强的变体，在参数规模较小的情况下提供了极具吸引力的性能-成本权衡。
英文摘要
Convolutional neural networks (CNNs), used widely and successfully in audio enhancement, capture long-range time-frequency dependencies only indirectly, through successive convolution and pooling. Here, we present U-PAST, a hybrid transformer-U-Net architecture that addresses this limitation through self-attention dependency-modeling in the complex spectrogram domain. U-PAST tokenizes a complex STFT representation, similarly to the magnitude spectrogram tokenization of the Audio Spectrogram Transformer (AST), applies a multi-layer transformer encoder, and reconstructs the enhanced complex spectrogram with a U-Net-style decoder. We evaluate four architectural variants with between 1.17M and 2.40M parameters on the DNS Challenge, VoiceBank-DEMAND, and LibriMix corpora under matched, acoustic mismatch, and two-dataset mismatch conditions. U-PAST attains the best SI-SDR of any evaluated model under acoustic mismatch and closely trails substantially larger convolutional and time-domain baselines by 0.26 dB to 0.63 dB SI-SDR under the remaining three conditions while achieving the strongest perceptual (DNSMOS) quality under dataset mismatch. The largest evaluated configuration, U-PAST-H (2.40M parameters), is consistently the strongest variant of the family, offering an attractive performance-to-cost trade-off at a small parameter footprint.
