Speech Enhancement with Impact Noise Activity Detection Based on the Kurtosis of an Instantaneous Power Spectrum

Naoto SASAOKA  Naoya HAMAHASHI  Yoshio ITOH  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E100-A   No.9   pp.1942-1950
Publication Date: 2017/09/01
Online ISSN: 1745-1337
Type of Manuscript: PAPER
Category: Digital Signal Processing
Keyword: 
speech enhancement,  noise activity detection,  impact noise,  kurtosis,  high-order cumulant,  

Full Text: PDF(3.2MB)
>>Buy this Article


Summary: 
In a speech enhancement system for impact noise, it is important for any impact noise activity to be detected. However, because impact noise occurs suddenly, it is not always easy to detect. We propose a method for impact noise activity detection based on the kurtosis of an instantaneous power spectrum. The continuous duration of a generalized impact noise is shorter than that of speech, and the power of such impact noise varies dramatically. Consequently, the distribution of the instantaneous power spectrum of impact noise is different from that of speech. The proposed detection takes advantage of kurtosis, which depends on the sharpness and skirt of the distribution. Simulation results show that the proposed noise activity detection improves the performance of the speech enhancement system.