Kernel fuzzy c-means speech emotion identification method combined with secondary identification of support vector machine
A speech emotion recognition and support vector machine technology, applied in the field of emotion recognition, can solve the problem that the predicted label is not optimal
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0032] Firstly, 30 sentences are selected from the four emotion corpora of happiness, anger, neutral and sadness in the German speech emotion database respectively as training corpus, and the rest as test corpus. The selected corpus is pre-emphasized, framed, and windowed. The frame length is 30ms, and the frame is shifted by 15ms. After the above processing, the 12-dimensional Mel cepstrum coefficient is used as the characteristic parameterized speech, and each sentence is only taken 80 frames of short speech features of about 1.4s, and each frame removes the first Mel cepstrum coefficient, so that each emotional training feature parameter and test feature parameter are obtained; in addition, 16-dimensional linear prediction coefficients are used as feature parameterization For speech, only 80-frame-length features are used as the training and testing feature parameters for secondary recognition. After obtaining the characteristic parameters, proceed as follows:
[0033] Step 1...
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