Performance analysis of speech enhancement using spectral gating with U-Net

Jharna Agrawal – Manish Gupta – Hitendra Garg

   Many speech processing systems’ crucial frontends include speech enhancement. Single-channel speech enhancement experiences a number of technological challenges. Due to the advent of cloud-based technology and the use of deep learning systems in big data, deep neural networks in particular have recently been seen as a potent means for complex classification and regression. In this work, spectral gating noise filter is combined with deep neural network U-Net to enhance the performance of speech enhancement network. Further, for performance analysis three distinct objective functions namely, Mean Square Error, Huber Loss and Mean Absolute Error are considered as loss functions. In addition, comparison of three different optimizers Adam, Adagrad and Stochastic Gradient Descent is presented. Proposed system is tested and evaluated on LibriSpeech and NOIZEUS datasets and compared to other state-of-the-art systems. It demonstrates that, in comparison to other state-of-the-art models, the proposed network outperformed them with PESQ scores of 2.737420 for training and 2.67857 for testing, along with better generalization ability.

Keywords: speech enhancement, spectral gating, deep neural network, U-Net, optimizers

[full-paper]