Voiceprint identification method
A technology of voiceprint recognition and variance, which is applied in speech analysis, instruments, etc., can solve the problem that the Gaussian mixture model cannot satisfy incremental learning, and achieve the effect of increasing the computational burden, reducing training time, and reducing the feature dimension
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0034] The invention discloses a voiceprint recognition method, comprising the following steps:
[0035] Step 1, preprocessing the segmented speech data of each speaker in the training speech set to form a set of sample sets corresponding to each speaker after preprocessing, and the speech data of a speaker uniquely corresponds to a sample set;
[0036] Step 2, extracting Mel cepstral coefficients for each sample in all sample sets;
[0037] Step 3: Select a sample set one by one and randomly select the Mel cepstrum coefficients of some of the samples, train the Gaussian mixture model on the sample set until all the sample sets are trained to obtain the Gaussian mixture model, and combine all the Gaussian mixture models into one model library;
[0038] Step 4, performing incremental learning on the samples that have not been selected for training in step 3 and the Gaussian mixture models of their corresponding sample sets one by one to obtain all optimized Gaussian mixture mo...
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