Speech enhancement post-processing method and device based on harmonic structure prediction

Abstract

The invention discloses a voice enhancement post-processing method and device based on harmonic structure prediction, and belongs to the field of information processing, and the method comprises the following steps: S1, carrying out the short-time Fourier transform of a voice signal of a microphone, and obtaining a time-frequency domain expression; s2, carrying out harmonic loss estimation and correction on the time-frequency domain signal to obtain an estimated power spectrum density; s3, estimating a time-frequency masking value according to the power spectrum density; and S4, according to the estimated time-frequency masking value, obtaining the frequency domain estimation of the target voice, and further obtaining the time domain estimation of the target voice. According to the method, the lost harmonic structure can be predicted to a certain extent, the recovered voice better conforms to the characteristics of the near-speaking voice, and the intelligibility and the voice perception quality are higher.

Description

technical field [0001] The invention belongs to the field of information processing, and in particular relates to a speech enhancement post-processing method and device based on harmonic structure prediction. Background technique [0002] In many applications such as voice conferencing systems, background noise can degrade the communication quality of the intercom system. It is one of the key technologies necessary for conference system related applications to suppress the noise signal collected by the microphone through an algorithm. However, when the noise suppression method suppresses the noise, the speech signal will also be damaged. Therefore, while suppressing noise, it is also necessary to consider how to enhance speech signals, especially the harmonic structure of speech. [0003] In the prior art, noise suppression and voice enhancement are key technologies for voice communication quality in conference systems or conference equipment. The traditional signal proce...

AI Technical Summary

Problems solved by technology

[0004] At present, the main disadvantages of the method for estimating the time-frequency masking value in the prior art are as follows: 1. The existing time-frequency masking method is easy to ignore the harmonic structure of the voice, resulting in the loss of some harmonics and affecting the communication quality; 2. The remote speaking scene Under the influence of reverberation, the high-frequency harmonics will be weakened, and the existing time-frequency masking method cannot recover the weakened high-frequency harmonics.

Images