Method and device for improving signal-to-noise ratio of voice signals in time domain

Abstract

The invention discloses a method for improving the signal-to-noise ratio of voice signals in a time domain. The method comprises the following steps of: searching a fundamental tone period of the voice signals from signals of a current frame in the time domain; according to the fundamental tone period, searching a best fundamental frequency wave crest position in the signals of the current frame,and calculating a fundamental frequency wave crest position corresponding to the best fundamental frequency wave crest position in each extended fundamental tone period in the signals of the current frame; and enhancing the signal amplitude close to the fundamental frequency wave crest position in each calculated fundamental tone period. In addition, the invention also discloses a device for improving the signal-to-noise ratio of the voice signals in the time domain. By using the technical scheme disclosed in the invention, the signal-to-noise ratio of the voice signals can be improved.

Description

technical field The invention relates to speech processing technology, in particular to a method and device for improving the signal-to-noise ratio of speech signals in the time domain. Background technique Since speech signals are often interfered by surrounding noises, speech recognition technology is required to identify speech from background noise. In the prior art, in order to facilitate speech recognition, a speech enhancement technology is usually used to improve the signal-to-noise ratio of a speech signal. Most of the current speech enhancement technologies are carried out in the frequency domain, such as the commonly used spectral subtraction method and Wiener filtering method. However, it is less carried out in the time domain. An existing speech enhancement technology in the time domain is: use the Teager operator to calculate the instantaneous energy envelope of the speech signal, then find the positions of each peak of the envelope, and then Enhancing the s...

AI Technical Summary

Problems solved by technology

However, this method is easily disturbed by noise. When the noise is strong, the position of each peak of the envelope may not completely correspond to the position of the peak of the fundamental frequency, but some correspond to the position of the peak of the noise. At this time, the position of the peak of the noise will be raised by mistake. reduce the signal-to-noise ratio

Images