Robust Speech Emotion Recognition Method Based on Compressed Sensing
A speech emotion recognition and compressed sensing technology, applied in speech recognition, speech analysis, instruments, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0076] figure 1 This system block diagram mainly includes two parts: acoustic feature extraction, sparse representation classifier training and testing.
[0077] 1. Acoustic feature extraction
[0078] From the German emotional speech sample database Berlin (see literature: Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W., Weiss, B. A database of German emotional speech. In: Proceedings of. Interspeech-2005 , Lisbon, Portugal, 2005, pp. 1-4.) selected seven emotional speech samples of anger, happiness, sadness, fear, disgust, boredom and neutral (no emotion), a total of 535 sentences. Gaussian white noise is added to each emotional speech sample selected, and pre-processed by pre-emphasis, frame division and windowing, where the frame length is 10ms. Then three aspects of the acoustic feature parameters are extracted: prosody feature, sound quality feature, and Mel-frequency cepstral coefficient MFCC. figure 2 The statistics of the extracted emotional acoustic featu...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 