Low Resources Online Single-Microphone Speech Enhancement with Harmonic Emphasis
Nir Raviv, Ofer Schwartz, Sharon Gannot · ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · 2022
In this paper, we propose a deep neural network (DNN)-based single-microphone speech enhancement algorithm characterized by a short latency and low computational resources. Many speech enhancement algorithms suffer from low noise reduction capabilities between pitch harmonics, and in severe cases, the harmonic structure may even be lost. Recognizing this drawback, we propose a new weighted loss that emphasizes pitch-dominated frequency bands. For that, we propose a method, applied only at the training stage, to detect these frequency bands. The proposed method is applied to speech signals contaminated by several noise types, and in particular, typical domestic noise drawn from ESC-50 and DE-MAND databases, demonstrating its applicability to ‘stay-at-home’ scenarios.