Voiceprint unlocking method integrating content recognition and speaker recognition
A technology of speaker recognition and content recognition, applied in speech recognition, speech analysis, instruments, etc., can solve the problem that voiceprint unlocking has not achieved good results
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0236] Below in conjunction with an example the present invention is described in further detail.
[0237] The key speech sample library contains 26 English letters, which are not case-sensitive. The speaker voice sample library contains 5 speaker sample voices. Both the key sample library speech and the speaker sample library speech were recorded in a laboratory environment. Set the system parameters, establish the recognition template of the key voice sample and the recognition template of the speaker voice sample, the system parameter settings are as follows:
[0238] Table 1 Speech modeling parameter settings
[0239]
[0240] According to the parameters set in Table 1, 26 key sample identification templates and 5 speaker identification templates are obtained. Set the current key as asdf, and the system linearly combines key sample a, key sample s, key sample d, key sample f identification template to form the current key identification template.
[0241] After the ...
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