Unlock instant, AI-driven research and patent intelligence for your innovation.

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.

Inactive Publication Date: 2014-10-22
TAIZHOU UNIV +2
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, in the existing research literature on speech emotion recognition, there is no robust recognition method using the discriminative properties of sparse representation in compressive sensing theory as a speech emotion recognition method.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Robust Speech Emotion Recognition Method Based on Compressed Sensing
  • Robust Speech Emotion Recognition Method Based on Compressed Sensing
  • Robust Speech Emotion Recognition Method Based on Compressed Sensing

Examples

Experimental program
Comparison scheme
Effect test

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...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a robust speech emotion recognition method based on compressive sensing. The recognition method includes generating a noisy emotion speech sample, establishing an acoustic feature extraction module, constructing a sparse representation classifier model, and outputting a speech emotion recognition result. The robust speech emotion recognition method has the advantages that effects of noise on emotion speech in the natural environment are fully considered, and the robust speech emotion recognition method under the noise background is provided; validity of feature parameters in different types is fully considered, extraction of feature parameters is extended to the Mel frequency cepstrum coefficient (MFCC) from prosodic and tone features, and anti-noise effects of the feature parameters are further improved; and the high-performance robust speech emotion recognition method based on the compressive sensing theory is provided through the sparse representation distinguishing in the compressive sensing theory.

Description

technical field [0001] The invention relates to the fields of speech processing and pattern recognition, in particular to a robust speech emotion recognition method based on compressed sensing. Background technique [0002] Human language not only contains text symbol information, but also carries information such as people's feelings and emotions. How to let the computer automatically analyze and judge the emotional state of the speaker through the speech signal, that is, the research on the so-called "speech emotion recognition" has become a hot spot in the fields of speech processing and pattern recognition. The ultimate goal of this research is to endow computers with emotional intelligence, so that computers can interact naturally, cordially and vividly like humans. This research has important application value in the fields of artificial intelligence, robotics, and natural human-computer interaction technology. [0003] At present, the research on speech emotion reco...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G10L15/02G10L15/06G10L15/08G10L25/03G10L25/63
Inventor 赵小明张石清
Owner TAIZHOU UNIV