Speech Enhancement via Deep Spectrum Image Translation Network
This addresses the critical problem of degraded speech for hearing aid and cochlear implant users, though it is incremental as it builds on existing image translation networks.
The paper tackled speech enhancement in unseen noise environments by proposing a VGG19-UNet architecture and a perceptually-modified spectrum image, resulting in improved quality and intelligibility as measured by PESQ and ESTOI scores.
Quality and intelligibility of speech signals are degraded under additive background noise which is a critical problem for hearing aid and cochlear implant users. Motivated to address this problem, we propose a novel speech enhancement approach using a deep spectrum image translation network. To this end, we suggest a new architecture, called VGG19-UNet, where a deep fully convolutional network known as VGG19 is embedded at the encoder part of an image-to-image translation network, i.e. U-Net. Moreover, we propose a perceptually-modified version of the spectrum image that is represented in Mel frequency and power-law non-linearity amplitude domains, representing good approximations of human auditory perception model. By conducting experiments on a real challenge in speech enhancement, i.e. unseen noise environments, we show that the proposed approach outperforms other enhancement methods in terms of both quality and intelligibility measures, represented by PESQ and ESTOI, respectively.