Signal classification method and device

A signal classification and signal technology, applied in speech analysis, speech recognition, instruments, etc., can solve the problem of high-efficiency, high-quality encoders, etc., and achieve high accuracy, low latency, and real-time effects.

Inactive Publication Date: 2013-03-27
ZTE CORP +1
View PDF7 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In real-time communication, existing signal classification algorithms cannot meet the requirements of high-efficiency and high-quality encoders due to complexity, delay and classification accuracy

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
  • Signal classification method and device
  • Signal classification method and device
  • Signal classification method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0079] This embodiment is the speech / music signal classification under the sampling rate of 32kHz, and the frame length L=1280. Under other conditions of frame length and sampling rate, the method of the present invention is also applicable. Classification process such as figure 1 As shown, the method includes:

[0080] Before classification, the classifier is trained first, including:

[0081] S1, input the training set signal, pre-process the input signal, and filter the input signal. The filter is a high-pass filter, which is used to filter out low-frequency DC components;

[0082] In this embodiment, the direct current component of 0-50 Hz can be filtered out, and of course, the direct current component in a higher or lower range can also be filtered out as required.

[0083] S2: Extract a short-term feature vector from the filtered signal. In this embodiment, the short-term feature vector includes the following parameters: logarithmic energy, zero-crossing rate, and sub...

Embodiment 2

[0131] This embodiment is the speech / music signal classification under the sampling rate of 32kHz, and the frame length L=1280. Under other conditions of frame length and sampling rate, the method of the present invention is also applicable. The method includes:

[0132] 401: Preprocessing and filtering the input signal, the filter is a high-pass filter, used to filter out low-frequency DC components;

[0133] 402: Perform feature calculation on the filtered signal. These include logarithmic energy features, zero-crossing rate features, and subframe logarithmic energy features.

[0134] 403: Calculate the short-term features based on the training set, and then extract n sets of long-term feature vectors with different durations, use the long-term feature vectors with different durations to train separately, and obtain n decision trees after proper pruning. One of the decision trees is figure 2 shown.

[0135] 404: After calculating the short-term features based on the tes...

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 provides a signal classification method. The signal classification method includes: acquiring a plurality of data units from signals to be classified, extracting m feature parameters from each data unit to form a short-term feature vector, selecting a group of data units from the data units, subjecting K short-term feature vectors corresponding to the group of data units to multiple statistical treatments so as to obtain a long-term feature vector comprising a group of statistical vectors Ys, s ranging from 1 to S, subjecting a j-th element of the short-term feature vectors from X1 to Xp to s-th statistical treatment so as to obtain a j-th element of the vectors Ys, and obtaining n long-term feature vectors corresponding to n groups of data units; sending the n long-term feature vectors into n classifiers obtained by pre-training according to a preset principle so as to obtain multiple classification results; and obtaining a final classification result from the multiple classification results according to a preset decision fusion mechanism. The invention further provides a signal classification device.

Description

technical field [0001] The invention relates to the fields of multimedia signal processing and pattern recognition, in particular to a signal classification method and device. Background technique [0002] Voice signals and music signals have different sound generation principles. Speech signal mainly refers to the sound produced when people speak. Music signals generally include a wider range of categories, such as orchestral music, percussion music, vocal music, and a mixture of multiple sound sources. These two types of signals are not only different in hearing, but in different occasions, the processing methods of the two types of signals are also different. [0003] In codec applications, speech signals are usually coded based on linear prediction, while music signals are widely coded in the transform domain. For the input of signals with uncertain categories, it is hoped that the signal category can be identified and then encoded in different ways, which can effecti...

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): G10L15/08G10L15/02
Inventor 卢敏窦维蓓覃春花袁浩唐庆余黎家力
Owner ZTE CORP
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