Cross-Representation Loss-Guided Complex Convolutional Network for Speech Enhancement of VHF Audio

Clarity of audio signal collected by voyage data recorders (VDR) is of great significance to reliable investigation of voyage accidents or vessal situation recovery. However, the very high-frequency (VHF) audio signal in VDR is often buried in various noises, resulting in risky understanding of audio content. To address this issue, a cross-representation loss-guided complex convolutional network (CRGCCN) is proposed. It consists of a complex encoding, a complex decoding, and a complex Conformer modules. In this work, absolute errors in frequency domain ( LLog-PCM) and relative errors in time domain ( LSi-SNRi) are integrated together in the cross-representation loss function, resulting in reasonable network parameters. In the proposed loss function, LLog-PCM contributes to reduce the absolute errors, and LSi-SNRi accounts for improving the robustness of the proposed network to different signal-to-noise ratios (SNRs). Experimental results show that the proposed model achieves best performance on both synthesized and real-world VHF audio datasets compared to several state-of-the-art methods.