Ecological voice recognition method based on multiband signal reconstruction

A signal reconstruction and sound recognition technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as poor recognition effect, increased decomposition times, and inability to suppress noise

Inactive Publication Date: 2013-12-25
FUZHOU UNIV
View PDF3 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If the number of decompositions is increased simply to improve the reconstruction accuracy, on the one hand, it will increase the amount of new calculations, on the other hand, it will not be able to suppress the noise, and the subsequent recognition effect will be poor.

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
  • Ecological voice recognition method based on multiband signal reconstruction
  • Ecological voice recognition method based on multiband signal reconstruction
  • Ecological voice recognition method based on multiband signal reconstruction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The invention proposes an ecological sound recognition method based on multi-band signal reconstruction, and builds a classification recognition framework based on deep learning. Firstly, the OMP sparse decomposition is used for the first-stage reconstruction to retain the main structure of the foreground sound; secondly, the remaining components of the previous stage decomposition are divided into frequency bands, and the reconstructed signal is adaptively adapted according to the frequency distribution of the foreground sound and background noise Compensation, complete the second stage of reconstruction; finally, extract composite anti-noise features according to the support set atomic time-frequency information and frequency domain information, and use the deep belief network (DBN) to classify and identify ecological sounds in different environments and SNR scenarios . like figure 1 As shown, it specifically includes the following steps:

[0041] S01: Perform OMP s...

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 relates to an ecological voice recognition method based on multiband signal reconstruction. The ecological voice recognition method comprises the steps of: firstly, using OMP (Orthogonal Matching Pursuit) sparse decomposition as a first-stage reconstruction, and reserving a main body structure of foreground voice; secondly, allocating remained components decomposed in the former stage according to bands, and carrying out adaptive compensation on reconstruction signals according to the frequency distribution of the foreground voice and background noise to complete a second-stage reconstruction; finally, extracting compound noise-proof characteristics according to atom time-frequency information and frequency-domain information in a support set, and carrying out classification and recognition on ecologic voice by using a high-credibility network under different environments and signal to noise ratio conditions. According to the ecological voice recognition method, the noise can be inhibited by adopting two times of reconstruction, and the reconstruction precision of the foreground voice is improved; better noise robustness is achieved under a natural environment.

Description

technical field [0001] The invention relates to an ecological sound recognition method based on multi-band signal reconstruction. Background technique [0002] Ecological sound recognition is to extract features and identify various sound signals in the natural environment. By analyzing and identifying the audio information contained in the environment, it can be used for invasion monitoring, species survey, etc. In the actual environment, a large amount of non-stationary noise interferes with sound recognition. Therefore, noise-resistant ecological sound recognition has important practical significance. [0003] At present, in audio signal processing, there are relatively many speech control and speaker recognition technologies, but there are relatively few researches on ecological environment sounds. Commonly used are the frequency domain feature Mel-Frequency Cepstral Coefficients (Mel-Frequency Cepstral Coefficients, MFCCs) and the time-frequency domain short-time Fou...

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): G10L15/20G10L15/08G10L15/02
Inventor 李应欧阳桢
Owner FUZHOU 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