Voiceprint identification method based on multi-type combination characteristic parameters
A technology that combines features and voiceprint recognition. It is used in digital data authentication, voice analysis, instruments, etc., and can solve problems such as low recognition accuracy and unstable voiceprint recognition system.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0095] Example
[0096] A voiceprint recognition method based on multiple types of combined feature parameters is characterized in that it includes the following steps:
[0097] S1: Acquisition and input of voice signals;
[0098] S2: pre-processing of voice signals, including pre-emphasis, framing and windowing;
[0099] S3: Speech signal combination feature parameter extraction: Extract MFCC, LPCC, △MFCC, △LPCC, energy, first-order difference of energy, and GFCC feature parameters to form a multi-dimensional feature vector, where: MFCC is the Mel frequency cepstrum coefficient, and LPCC is Linear prediction cepstrum coefficient, △MFCC is the first-order difference of MFCC, △LPCC is the first-order difference of LPCC, and GFCC is the cepstrum coefficient of Gammatone filter;
[0100] S4: Use genetic algorithm to screen the multi-dimensional feature vectors in step S3, use the medium error rate EER in the GMM-UBM recognition process as the evaluation function, and select the feature ve...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap