Voice signal processing method and device
A voice signal processing and voice signal technology, applied in the field of communication, can solve the problem of poor discrimination effect of non-stationary noise, and achieve the effect of improving the accuracy of judgment
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment approach
[0051] In a first manner, it can be determined whether the energy distribution of the speech signal frame is concentrated by calculating the number of speech peaks in the frequency domain of the speech signal frame. When the number of speech peaks in the frequency domain is greater than the first predetermined threshold, it can be determined that the energy distribution of the speech signal frame is not concentrated. Preferably, in the implementation process, the first predetermined threshold may be set to a number greater than 3.
[0052] In the second way, it is also possible to determine whether the energy distribution of the voice signal frame is concentrated by calculating the voice peak energy ratio (Voice Peak Energy Ratio, referred to as VPER) of the voice signal frame. The ratio can refer to the auxiliary voice peak and the main voice peak. energy ratio. When the VPER is less than the second predetermined threshold, it can be determined that the energy distribution o...
Embodiment 2
[0105] In this preferred embodiment, the speech enhancement solution is further described in detail with reference to the accompanying drawings.
[0106] 1. Extraction of speech parameters
[0107] Figure 7 is a schematic diagram of the speech frame parameters in the spectrum domain according to the second embodiment of the present invention, such as Figure 7 As shown, the figure shows the parameters of a frame of speech signal in the spectral domain. Among them, the coordinate of the vertical axis is the frequency spectrum amplitude, the coordinate of the horizontal axis is the sampling point in the frequency domain, and the sampling point interval is described by taking 31.25 Hz as an example. Figure 7 The frequency domain voice peak bandwidth (VPB) of a voice frame is shown in the figure. There are two voice peaks in this figure. The matrix composed of the starting point and the ending point of the frequency band is denoted as VPB1 and VPB2, respectively. They are comp...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com