An Adaptive Speech Enhancement System Based on Noise Level Estimation and Lateral Inhibition

Author: Choi, Jae Seung

Source: Acta Acustica united with Acustica, Volume 93, Number 4, July/August 2007 , pp. 632-644(13)

Publisher: S. Hirzel Verlag

Key:
Free Content - Free Content
New Content - New Content
Subscribed Content - Subscribed Content
Free Trial Content - Free Trial Content

Abstract:

In speech recognition under a noisy environment, a system is needed that can reduce noise, while enhancing speech. The human auditory system has an excellent analytical spectrum mechanism for speech enhancement. Accordingly, this paper proposes an adaptive method which is inspired by known human auditory mechanism, called lateral inhibition. This method first estimates noise intensity using a neural network, then adjusts frame by frame the coefficients of both the lateral inhibition and the amplitude component according to the noise intensity for each input frame. The proposed system is compared with the results of a conventional spectral subtraction method and minimum mean-square error log-spectral amplitude (MMSE-LSA) estimator at different noise levels. Experiments confirm that the proposed system is effective for speech degraded by various noises using objective (global SNR and spectral distortion) and subjective mean opinion score (MOS) evaluations.

Document Type: Research article

The full text electronic article is available for purchase. You will be able to download the full text electronic article after payment.

$33.00 plus tax      Refund Policy

 

OR

Back to top

Key:
Free Content - Free Content
New Content - New Content
Subscribed Content - Subscribed Content
Free Trial Content - Free Trial Content
Share this item with others: These icons link to social bookmarking sites where readers can share and discover new web pages.
Page Help Click here for Page Help
Shopping cart
Tools
Sign in






Need to register?
Sign up here
Text size: A | A | A | A