A speech enhancement algorithm using computational auditory scene analysis with spectral subtraction

• Published in: 2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) pp. 6 - 10
• Main Authors: Cong Guo, Like Hui, Wei-Qiang Zhang, Jia Liu
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2016
• Subjects: computational auditory scene analysis (CASA); deep neural network (DNN); Neural networks; Signal processing algorithms; Signal to noise ratio; Speech; Speech enhancement; Time-frequency analysis; Training
• DOI: 10.1109/ISSPIT.2016.7886000

Computational auditory scene analysis (CASA) system is well used in speech enhancement area in recent years. We propose a new system that combines CASA and spectral subtraction to get better enhanced speech. The CASA part consists of the latest method deep neural networks (DNNs). The original way to reconstruct the denoise signal is to use the estimated masks with direct overlap-add method ignoring the information of noise within the frames. In our system, we estimate self-adapted thresholds for each channel by Gaussian Mixture Model from the estimated ratio masks (ERMs) to separate noise and speech of each channel. In this way, we make full use of the information within frames. The results show increase in both objective and subjective evaluation.