Speech emotion recognition method based on semantic cells

A speech emotion recognition and cell technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problem of large data space occupied by the generated model, achieve the effect of maintaining recognition accuracy and overcoming the large data space occupied

Active Publication Date: 2014-12-10
ZHEJIANG UNIV
View PDF5 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention utilizes the advantages of the cognitive structure of semantic cells to overcome the shortcomings of the existing speech emotion recognition algorithm generation model that occupies a large data space, and can maintain the recognition accuracy similar to that of the SVM algorithm

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
  • Speech emotion recognition method based on semantic cells
  • Speech emotion recognition method based on semantic cells
  • Speech emotion recognition method based on semantic cells

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] In order to enable those skilled in the art to better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with specific embodiments and accompanying drawings.

[0075] figure 1 Shown is the flowchart of the speech emotion recognition method based on semantic cell of the present invention, and this method comprises:

[0076] (1) Establish a voice database

[0077]Need to set up emotion voice database (voice database) in advance in the present embodiment, each record in the voice database needs to comprise: recording data (voice signal), the unique identifier (as numbering) of the speaker in the recording, the speaker's name in the recording The expression's emotion classification mark (such as happiness). The speech database used in this embodiment is the CASIA corpus (Tao Jian-hua, Yu Jian, Kang Yong-guo. An expressive mandarin...

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 speech emotion recognition method based on semantic cells. The speech emotion recognition method based on the semantic cells includes steps: building a voice library, preprocessing each speech signal in the voice library, extracting emotion features of each speech signal in the voice library, calculating a feature vector of each speech signal according to an extraction result, using training of the feature vectors to obtain a mixed model based on the semantic cells, using the obtained mixed model as a recognition model of a classifier, and using the recognition model to recognize an emotion category of a speech signal to be recognized. The speech emotion recognition method based on the semantic cells builds the recognition model for speech emotion by building the mixed model based on two layers of the semantic cells which can enable a user to recognize a speaker and emotion of the speaker, and when the recognition model built by using the speech emotion recognition method based on the semantic cells is used to recognize the speech emotion, accuracy is high, the quantity of data needed for storing the recognition model is effectively reduced on the premise that the same recognition accuracy as an SVM algorithm is guaranteed, and furthermore the speech emotion recognition method based on the semantic cells has advantages in space complexity and the recognition accuracy.

Description

technical field [0001] The invention relates to the technical field of speech recognition, in particular to a speech emotion recognition method based on semantic cells. Background technique [0002] Speech is a sound symbol used to express language, and it is one of the important media for human to communicate with each other and convey emotion. Speech emotion recognition is an important research direction in the field of affective computing. Its goal is to recognize the speaker's emotional state through speech signals, and finally realize natural, friendly, and vivid human-computer interaction. [0003] Speech emotion recognition technology can be used in many fields such as interactive teaching, intelligent vehicle systems, and smart home appliances. For example, in online movies and computer tutorial applications developed by Schuller, the system responds to users according to the detected emotional information (Schuller B, Rigoll G, Lang M.Speech emotion recognition com...

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 Applications(China)
IPC IPC(8): G10L25/63G10L15/06
Inventor 孙凌云何博伟汤永川李彦郑楷洪
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap