Method for quickly recognizing speech emotion category based on long and short term memory network

A long-short-term memory and speech recognition technology, which is applied in speech analysis, instruments, etc., can solve the problems of increasing computational complexity and achieve the effects of reducing computational complexity, good application prospects, and reducing the amount of matrix calculations

Pending Publication Date: 2021-06-29
NANJING INST OF TECH
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above algorithms increase the computational complexity while optimizing the memory capacity of LSTM

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
  • Method for quickly recognizing speech emotion category based on long and short term memory network
  • Method for quickly recognizing speech emotion category based on long and short term memory network
  • Method for quickly recognizing speech emotion category based on long and short term memory network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The present invention will be further described below in conjunction with the accompanying drawings.

[0049] The invention discloses a method for quickly identifying speech emotion categories based on a long-short-term memory network, which includes the following steps:

[0050] Step A, extract frame-level speech features with timing information from the original speech data, wherein, the speech features retain the timing information in the original speech data through the sequence relationship between speech frames, and the dimension of the speech features varies with the original Varies with the actual length of the voice data. The detailed speech feature set is shown in Table 1 below:

[0051] Table 1

[0052] voice features describe voiceProb Ratio of voiced sound HNR glottal harmonic-to-noise ratio F0 Baseband F0raw Original base frequency without unvoiced threshold F0env F0 envelope jitterLocal Periodic first...

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 method for quickly recognizing a speech emotion category based on a long and short term memory network. The method comprises the following steps: extracting frame-level speech features with time sequence information from an original speech data sample; creating an attention mechanism-based improved LSTM (Long Short Term Memory) model through a soft attention model; training the improved LSTM model by using a known original voice data sample and a voice emotion category thereof to obtain an emotion category recognition model; performing emotion recognition test verification on the emotion category recognition model; inputting an unknown original voice data sample into the emotion category recognition model for recognition, and outputting a corresponding voice emotion category; according to the method, the conventional LSTM model is optimized through the attention mechanism to obtain the improved LSTM model, the matrix calculation amount is effectively reduced on the premise of ensuring the performance, the speech emotion category recognition performance is improved, and the method has a good application prospect.

Description

technical field [0001] The invention relates to the technical field of speech emotion recognition, in particular to a method for quickly recognizing speech emotion categories based on a long-short-term memory network. Background technique [0002] Speech is one of the important ways for human beings to express emotion, and emotion recognition using it as a medium is of great significance to the research of intelligent human-computer interaction. Earlier work on speech emotion recognition mainly focused on machine learning algorithms such as support vector machines, Bayesian classifiers, and K-nearest neighbors. At present, with the introduction of deep learning, speech emotion recognition has been further developed. [0003] Although the early work promoted the research of speech emotion, due to the influence of traditional machine learning that can only accept fixed-length data as input, static speech emotion features with fixed dimensions are currently the most used. For...

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): G10L25/63G10L25/30G10L25/03
CPCG10L25/03G10L25/30G10L25/63
Inventor 颜思瑞丁凯星谢跃陈允韬王超
Owner NANJING INST OF 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