Method for recognizing emotion points of Chinese pronunciation based on sound-track modulating signals MFCC (Mel Frequency Cepstrum Coefficient)
A Chinese and emotional technology, applied in the information field, can solve the problem of low average recognition rate of emotional points
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0048] The technical scheme of the present invention will be further explained below in conjunction with the drawings.
[0049] figure 1 It is a flow chart of using electroglottic diagram signals and speech signals for feature extraction, training models and identifying emotional points. It is mainly divided into two parts: the acquisition of Chinese voice emotional points and the recognition of Chinese voice emotional points.
[0050] 1. To acquire the emotional points of Chinese speech, the method steps are as follows:
[0051] Step 1. Formulate the recording specifications of emotional speech database, the specific rules are as follows;
[0052] (1) Speakers: Between the ages of 20 and 25, with a bachelor's degree, the number is 5 males and 5 females, 10 people.
[0053] (2) Speaking content: 28 interjections are selected as emotional points, and each emotional point is recorded 3 times during the experiment.
[0054] (3) Emotion classification: angry, happy, sad, surprised, fearful, ...
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