A Novel Binaural Cue Preservation Loss for DNN-Based Binaural Speech Enhancement
2026-08-17 • Sound
Sound
AI summaryⓘ
The authors address how hearing aids can reduce background noise without messing up how we hear sounds from left and right ears, which helps us know where sounds come from. They introduce two new ways to train computers to keep these left-right sound differences more accurately. One method checks the whole sound relationship between ears, while the other looks at common sound cues together. Their tests show these methods reduce noise well and keep natural sound direction better than older methods.
binaural speech enhancementhearing aidsinteraural level differences (ILD)interaural phase differences (IPD)deep neural networksnoise reductionbinaural cuesmasking distortionspatial localization
Authors
Jayteerth Amble, Thomas Haubner, Hendrik Schröter, Christoph Hoog Antink, Henning Puder
Abstract
Binaural speech enhancement for hearing aids aims to reduce noise while preserving the interaural cues needed for spatial localization. Although deep neural network-based methods achieve strong noise reduction, they often distort the rela- tionship between the left and right signals. In this paper, we propose two novel binaural cue preservation losses. First, a binaural reconstruction error loss that directly penalizes masking-induced distortion in the relationship between the left and right spectra, providing a more direct measure of the binaural consistency than conventional separate interaural level differences (ILD) and interaural phase differences (IPD) errors as in prior work. Second, a binaural cue loss that jointly models ILD and IPD to better preserve the binaural structure. Experimental results show that both proposed losses maintain strong noise reduction performance and reduce masking- induced distortion compared to the state-of-the-art baseline cue loss, while the second proposed joint binaural cue loss also outperforms the baseline in ILD preservation.