Voiceprint identification method
A voiceprint recognition and voice feature technology, applied in voice recognition, voice analysis, instruments, etc., can solve the problems of large amount of model data, limited algorithm use, high computational complexity, etc., to save storage resources, small amount of feature data, The effect of small amount of calculation
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0022] The preferred embodiments of the present invention are described in detail below, so that the advantages and features of the present invention can be more easily understood by those skilled in the art, so as to define the protection scope of the present invention more clearly.
[0023] See attached Figure 5 , a voiceprint recognition method, comprising the steps of:
[0024] 1) See attached figure 1 , the speech feature space establishment step, the speech of different backgrounds and different human voices is divided into 20ms as a frame, the 10ms frame is shifted to take out the speech frame (speech segment), the silence is removed in units of frames, and the cepstral transformation is performed on the speech frame, There are 12 coefficients left in each frame, and the 12 coefficients constitute speech feature points. The speech feature points of all speech segments form a speech feature point set, that is, a speech feature space.
[0025] 2) See attached figure...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 