A Robust Scale Contour Feature Extraction Algorithm Based on Kernel Norm

A technology of contour features and nuclear norms, applied in speech analysis, instruments, etc., can solve the problem that the chord feature extraction scheme does not consider the structure of music signals, etc., and achieve the effect of reducing the time of the algorithm and removing damage

Inactive Publication Date: 2020-04-28
TIANJIN UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] It can be seen that most chord feature extraction schemes do not consider the structure of the music signal on the frequency spectrum, apply some known assumptions, and use some simple processing methods to optimize the chord features

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
  • A Robust Scale Contour Feature Extraction Algorithm Based on Kernel Norm
  • A Robust Scale Contour Feature Extraction Algorithm Based on Kernel Norm
  • A Robust Scale Contour Feature Extraction Algorithm Based on Kernel Norm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0022] Step 1. Music signal conversion: Convert the to-be-input music signal into standard audio with a sampling rate of 22050Hz / 16bit / single channel as the audio signal to be referenced.

[0023] Step 2. Perform windowing processing on the music signal x(n), the window function is W(k), where k is the window width of the window function, thereby obtaining the signal time domain matrix X k×m , Where X ·,M =x(k·m / 2:k·m / 2+m)·W(k), where m is the number of frames obtained after framing, and then Fourier Transform (Fourier Transform) is performed to obtain the time-frequency matrix D of the music signal =F·X, where F is the Fourier transform matrix;

[0024] Step 3. Frequency spectrum low-ranking and noise removal: It can be seen from the frequency spectrum that the music signal mainly contains two components: harmonic components and sparse noise. Harmonic components ...

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 robust musical scale outline feature extraction algorithm based on nuclear norms. Step1, signal converting of to-be-input musical signals; step 2, performing windowing processing and Fourier transform of musical signals to obtain a time frequency matrix of the musical signals and determine a start and ending beat point; step 3, using nuclear norm constraint to perform frequency spectrum low-rank transformation on the rank of the time frequency matrix and simultaneously using a norm to constrain a noise point in a matrix and using the following convex optimization problem to perform low-rank transformation and noise removing on the signal frequency spectrum; step 4, in an iterative constraint process, realizing a threshold adaptive adjusting algorithm through utilization of low-rank characteristics of the frequency spectrum; and step 5, performing effective dimension-reduction processing on the time frequency matrix to obtain 12-dimensional chord characteristics. Compared with the prior art, the algorithm of the present invention extracts robust chord features, effectively reduces the time of the algorithm, can accurately restore the musical scale outline features of different types and styles of music signals.

Description

Technical field [0001] The invention belongs to the field of audio signal analysis in a computer auditory system, and particularly relates to a scale contour feature extraction algorithm. Background technique [0002] The harmonic component of music is an important element of music and an important subject in the field of music information retrieval. The fundamental frequency of different frequencies of the audio signal and its harmonic components are important components that constitute chords and affect the color of music. In addition, the extension of different frequency components in time constitutes a key factor for chord progression. Intuitively speaking, the music within the chord duration will show a certain structure in the frequency domain-low-rank characteristics. The extraction of musical chord features is part of the audio signal analysis in the computer auditory system. This field mainly deals with various information separated from the sound signal. At the same ...

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): G10L21/013G10L21/0224G10L21/0232G10L25/18G10L25/45
CPCG10L21/013G10L21/0224G10L21/0232G10L25/18G10L25/45G10L2021/0135
Inventor 李锵王蒙蒙关欣
Owner TIANJIN 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