Speech emotion recognition method based on spectral features and ELM
A speech emotion recognition and spectral feature technology, applied in speech recognition, speech analysis, instruments, etc., to achieve the effect of improving accuracy, learning speed, and good recognition performance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0030] The present invention comprises the following steps in the realization process:
[0031] (1) The feature extraction of the original speech signal includes prosodic features (fundamental frequency, short-term average energy, short-term average amplitude, silence time ratio, short-term average zero-crossing rate, speech rate), sound quality features (formant frequency, breath sound, loudness);
[0032] (2) Proposed to use Teager Energy Operators Cepstral Coefficients (TEO) algorithm to extract Mel-scale Frequency Cepstral Coefficients (Mel-scale Frequency Cepstral Coefficients, MFCC) and Cochlear Filter Cepstral Coefficients (Cochlear Filter Cepstral Coefficients) in Mel scale frequency domain , CFCC), get teMFCC eigenvalue and teCFCC eigenvalue;
[0033] (3) weighting the teMFCC eigenvalues and teCFCC eigenvalues to obtain the teCMFCC eigenvalues, and fusing them with the basic eigenvalues (prosodic features, sound quality features) to construct a feature matrix; ...
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