Speech emotion recognition method based on parameter migration and spectrogram

A speech emotion recognition and recognition method technology, applied in the field of speech processing technology and sentiment analysis, can solve the problems of extracting spectrogram features, not fully considering the time-frequency two-domain characteristics of spectrogram, and low recognition rate, so as to improve training Speed, improve the effect of recognition accuracy

Active Publication Date: 2018-09-28
GUILIN UNIV OF ELECTRONIC TECH
View PDF6 Cites 58 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these studies did not build a good model to extract spectrogram features, did not fully consider the characteristics of t...

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 parameter migration and spectrogram
  • Speech emotion recognition method based on parameter migration and spectrogram
  • Speech emotion recognition method based on parameter migration and spectrogram

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0038] refer to figure 1 : A speech emotion recognition method based on parameter transfer and spectrogram, including the following steps:

[0039] 1): Collect speech emotion data from the Chinese emotion database of the Institute of Automation, Chinese Academy of Sciences and preprocess the speech emotion data. The speech emotion data includes 6 emotions: anger, fear, happiness, neutrality, sadness, and surprise;

[0040] 2): Construct a network model based on pre-trained convolutional neural network;

[0041] 3): Perform parameter migration and training on the network model in step 2).

[0042] The pretreatment described in step 1) comprises the steps:

[0043] ①: Collect 6 kinds of speech emotion data;

[0044] ②: Pre-emphasize the voice waveform signal of each piece of voice emotion data, divide the pre-emphasized voice waveform signal into frames, and then window the framed voice waveform signal to reduce leakage;

[0045] (1): The voice waveform signal will attenuate...

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 parameter migration and a spectrogram, and the method comprises the following steps: 1), collecting the speech emotion data from aChinese emotion database of Institute of Automation, Chinese Academy of Sciences, and carrying out the preprocessing of the speech emotion data, wherein the speech emotion data contains six emotions:anger, fear, happiness, neutral emotion, sadness, and surprise; 2), constructing a network model based on a pre-trained convolutional cyclic neural network; 3), carrying out the parameter migration and training of the network model at step 2). The method can achieve the extraction of the emotion features of the spectrogram in the time and frequency domains, improves the recognition accuracy, alsocan learn the pre-training technology, and improves the network training speed.

Description

technical field [0001] The invention relates to the fields of speech processing technology and emotion analysis technology, in particular to a speech emotion recognition method based on parameter transfer and spectrogram. Background technique [0002] As one of the important carriers of human communication, speech not only carries semantic content but also contains rich emotional information. Speech emotion recognition integrates pattern recognition, signal processing, bionics and other disciplines, and plays an extremely important role in the development of artificial intelligence and human-computer interaction. The purpose of speech emotion recognition is to enable the machine to automatically recognize the speaker's current emotional state from the human speech signal, so that the computer has a more humane function. [0003] According to current research, the features used for emotion recognition in speech signals can be roughly divided into three categories: prosodic f...

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
IPC IPC(8): G10L25/63G10L25/30G10L25/45G10L25/24G10L25/15G10L15/06G06K9/62
CPCG10L15/063G10L25/15G10L25/24G10L25/30G10L25/45G10L25/63G06F18/2411G06F18/253
Inventor 缪裕青邹巍刘同来蔡国永文益民缪永进汪俊宏
Owner GUILIN UNIV OF ELECTRONIC TECH
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