PRS Winter 2019, 20 Hendrik Schröter Learning based Noise Reduction using Complex Linear Coding

Noise reduction is an important part of modern hearing aids and is included in most commercially available devices. Deep learningbased stateoftheart algorithms, however, either do not consider realtime and frequency resolution constrains or result in poor quality under very noisy conditions. To improve monaural speech enhancement in noisy environments, we propose CLCNet, a framework based on complexvalued linear coding. First, we define complex linear coding (CLC) motivated by linear predictive coding