Reinforced spectral subtraction method to enhance speech signal

We propose a speech enhancement technique. It is based on the spectral subtraction method, which is one of the major techniques of speech enhancement. However, the enhanced output speech signal of the spectral subtraction method is corrupted by "musical noise". The musical noise is an offe...

Full description

Saved in:
Bibliographic Details
Main Authors: Ogata, S., Shimamura, T.
Format: Conference Proceeding
Language:English
Subjects:
Discrete Fourier transforms
Filtering algorithms
Humans
Iterative algorithms
Noise reduction
Signal processing
Signal to noise ratio
Speech enhancement
Wiener filter
Working environment noise
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose a speech enhancement technique. It is based on the spectral subtraction method, which is one of the major techniques of speech enhancement. However, the enhanced output speech signal of the spectral subtraction method is corrupted by "musical noise". The musical noise is an offensive noise for human listening. To reduce the musical noise, we adopt an iterative algorithm. The iterative algorithm is derived from the same idea as Wiener filtering for speech enhancement. We use the output signal of the spectral subtraction method as the input signal again. This process is iterated a few times. Each time we iterate the spectral subtraction method, we estimate the noise signal and subtract it. Therefore we can further reduce the musical noise with each iteration.
DOI:10.1109/TENCON.2001.949588