Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Sound classification method without digital feature extraction and calculation

A classification method and digital feature technology, applied in speech analysis, instruments, etc., can solve the problem of high system hardware costs, achieve the effect of reducing computing power requirements, reducing operating costs, and saving digital calculations

Inactive Publication Date: 2021-04-09
爱荔枝科技(北京)有限公司
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Second, the sound feature extraction algorithm needs to run on a digital processor, requiring the system to provide a large amount of calculation and memory, which has high requirements for system computing power and memory, resulting in high system hardware costs

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
  • Sound classification method without digital feature extraction and calculation
  • Sound classification method without digital feature extraction and calculation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] The following description serves to disclose the present invention to enable those skilled in the art to carry out the present invention. The preferred embodiments described below are only examples, and those skilled in the art can devise other obvious variations.

[0017] Such as figure 2 As shown, the sound classification method provided by the embodiment of the present invention directly processes the analog signal collected by the microphone, uses an analog filter bank to divide the analog signal received by the microphone into multiple frequency bands, and then uses an analog integrator to analyze each The analog signal on the frequency band is integrated to obtain the analog signal of multiple frequency bands, and these analog signals are the "analog characteristics" of the sound. These analog features are converted from analog to digital to feature signals in the digital domain, and then compared with the sound model to obtain the corresponding type of sound. ...

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 sound classification method without digital feature extraction and calculation. The method comprises the following steps of: 1, obtaining an analog recording signal through a recording system, and obtaining analog signals of N frequency bands through an analog filter group formed by analog circuits, N being the number of frequency bands required by a feature vector; 2, respectively processing the analog signals of the N frequency bands generated in the step 1, and carrying out energy calculation; 3, converting the analog energy characteristics of each frequency band into digital energy characteristics through an analog-to-digital converter; and 4, performing matching calculation on the digital energy characteristics of each frequency band and the model data to obtain the type of the sound. According to the method, an analog signal processing method is adopted to replace a digital signal processing method to obtain sub-band energy feature vectors required by simple sound classification, and the method can be suitable for simple sound classification.

Description

technical field [0001] The invention belongs to the technical field of speech, and in particular relates to a sound classification method. Background technique [0002] Sound classification is a method used to distinguish sound categories. The sound classification task is different from the speech recognition task. For example, the sound classification task of distinguishing the cry of a baby from the normal environmental sound generally requires lower feature vectors than speech recognition. Speech recognition tasks generally require the extraction of formant features in speech, so advanced features such as Mel-frequency cepstral coefficients or linear perceptual predictions are required. These features need to be extracted from digital audio signals, and the extraction process requires a large number of digital operations. , will involve fast Fourier transform, trigonometric function calculation, exponential calculation and logarithmic calculation. Generally, one frame of...

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): G10L25/03G10L25/21G10L25/51
CPCG10L25/03G10L25/21G10L25/51
Inventor 陈盛马文亮
Owner 爱荔枝科技(北京)有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products