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

Animal sound detection method based on multi-band energy distribution in low signal-to-noise ratio environment

A technology with energy distribution and low signal-to-noise ratio, applied in speech analysis, instruments, etc., can solve problems such as detection effect limitations, and achieve good detection performance, low noise environment, and good robustness

Active Publication Date: 2019-11-12
FUZHOU UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for the classification and detection of sound events with lower signal-to-noise ratio, the detection effect of this method is limited.

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
  • Animal sound detection method based on multi-band energy distribution in low signal-to-noise ratio environment
  • Animal sound detection method based on multi-band energy distribution in low signal-to-noise ratio environment
  • Animal sound detection method based on multi-band energy distribution in low signal-to-noise ratio environment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0051] The existing methods for classification and detection of low signal-to-noise ratio sound events are as follows: figure 1 As shown in the thin line box in the lower part, that is, gray-scale logarithmic spectrogram, image feature extraction, and SVM classification. Using this method, the classification of sound events achieves better results. The detection rates of sound events with SNR of 20dB and 10dB are respectively 87.8% and 87.1%, especially in the case of 0dB, the detection rate reaches 74.4%. figure 1 As shown in the dotted line box in , the image feature extraction is through Jet mapping, and the gray logarithmic spectrum is mapped into three sub-images, and each sub-image is divided into 9×9 blocks, and then the mean value and variance of each block are extracted, that is, a total of 486 (2×3×9×9) dimensional vectors are used as featur...

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 animal sound detecting method based on multiband energy distribution in a low signal-to-noise-ratio environment. The animal sound detecting method comprises the following steps: S1, carrying out time-frequency analysis on a to-be-detected sound sample by adopting a multi-filter bank, thus obtaining a multiband spectrogram; S2, analyzing the frequency and energy distribution of the multiband spectrogram, thus obtaining a multiband energy distribution diagram; S3, carrying out blocked DCT on the multiband energy distribution diagram, and extracting low-frequency coefficients in the DCT coefficient matrix as the characteristics of the to-be-detected sound sample; S4, carrying out treatment on a plurality of trained sound samples according to the above steps, thus obtaining the characteristics of the trained sound samples, and training the characteristics of the trained sound samples by adopting a random forest classifier, thus obtaining a random forest; and S5, substituting the characteristics of the to-be-detected sound sample into the random forest for testing, thus determining the type of the to-be-detected sound sample. Compared with the prior art, the method provided by the invention has good robustness under the low signal-to-noise-ratio environment.

Description

technical field [0001] The invention relates to an animal sound detection method based on multi-band energy distribution in a low signal-to-noise ratio environment. Background technique [0002] Low SNR sound event detection attempts to detect, classify, and identify relatively weak sound objects embedded in various noise and reverberant audio signals. Recently, acoustic event detection has attracted much attention. With the rapid growth of multimedia data in the network, multimedia search based on audio data has great application value. At the same time, sound event detection is also one of the key components of the analysis environment. For example, it is for audio forensics, environmental sound recognition, biological sound monitoring, acoustic scene analysis, real-time military focus detection, location tracking and sound source classification, patient monitoring, abnormal event monitoring and fault diagnosis, and submission of key information for early maintenance etc...

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): G10L17/20G10L17/26G10L25/18G10L17/04
CPCG10L17/04G10L17/20G10L17/26G10L25/18
Inventor 李应王巧静
Owner FUZHOU UNIV