Title :
An auditory-based adaptive speech enhancement system by neural network according to noise intensity
Author :
Choi, Jaeseung ; Okamoto, Jun ; Nakajima, Shigeyoshi ; Suzuki, Yuya ; Hosokawa, Slioichi
Author_Institution :
Dept. of Inf. & Commun. Eng., Osaka City Univ., Japan
Abstract :
This paper presents an adaptive optimization method applying the auditory mechanism which is called lateral inhibition. This method first estimates noise intensity using a neural network, then adjusts adaptively the coefficients of both lateral inhibition and amplitude component according to the noise intensity for each input frame. It is confirmed that this method is effective for speech degraded not only by white noise but also by colored noise, judging from spectral distortion measurement
Keywords :
adaptive signal processing; backpropagation; optimisation; parameter estimation; perceptrons; random noise; speech enhancement; white noise; adaptive optimization method; amplitude component; auditory-based adaptive speech enhancement system; colored noise degraded speech; lateral inhibition; neural network; noise intensity; white noise degraded speech; Adaptive systems; Amplitude estimation; Colored noise; Degradation; Distortion measurement; Neural networks; Noise level; Optimization methods; Speech enhancement; White noise;
Conference_Titel :
Circuits and Systems, 1999. 42nd Midwest Symposium on
Conference_Location :
Las Cruces, NM
Print_ISBN :
0-7803-5491-5
DOI :
10.1109/MWSCAS.1999.867802