Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A method for automatic identification of sound quality of stringed instruments

A discriminant method and technology of stringed instruments, applied in the interdisciplinary field of musicology and information science, can solve problems such as inaccurate judgment, high labor cost, and fluctuation of reference standards

Active Publication Date: 2019-06-11
XI AN JIAOTONG UNIV
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method will cause inaccurate judgments due to the aesthetic fatigue of the judges, fluctuations in reference standards, subjective aesthetic tendencies, and differences in the on-site acoustic environment.
In addition, the high labor cost is also a shortcoming of manual evaluation

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 method for automatic identification of sound quality of stringed instruments
  • A method for automatic identification of sound quality of stringed instruments
  • A method for automatic identification of sound quality of stringed instruments

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0069] The embodiments of the present invention will be described in detail below with reference to the examples.

[0070] Step 1: Automatic recognition of instrument type

[0071] Each type of stringed instrument and the timbre of its performance is unique, so the judging methods and parameters used are different. In order to realize the automation of sound quality evaluation, it is first necessary to automatically identify the type of musical instrument. The specific identification plan includes the following links:

[0072] 1) Extract 3 audio features to describe the type of instrument

[0073] a) Spectral barycenter G of each frame

[0074]

[0075] Among them, m is the window width, usually you can choose m=20ms, f n is the nth harmonic frequency of the sound, A n is the amplitude at the nth harmonic. Through the sliding of the sliding window, a series of spectral centers of gravity can be obtained, and the maximum value G can be calculated. M , the minimum valu...

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

A method for automatically discriminating the sound quality of stringed musical instruments. First, the type of musical instrument and its performance mode are automatically identified; secondly, the dynamic and static features of the performance of the instrument are extracted according to the type and performance mode of the musical instrument; finally, the extracted features are used as input, Using the random forest model as a classifier for training and classification, and continuous processing of the results, the present invention forms an instrumental sound quality expression form that combines time domain and frequency domain, static and dynamic integration by introducing new features; for different The characteristics of the expression form are recognized by the corresponding sound quality recognition algorithm, and the recognition results are synthesized to obtain the final recognition result, which realizes the automatic evaluation of the sound quality of stringed instruments. This method comprehensively considers the characteristics of the stringed instrument playing process, the time series model, and the characteristics of the audio time domain and frequency domain, and designs a complete set of sound quality learning-recognition technology for stringed instrument performance.

Description

technical field [0001] The invention belongs to the cross technical field of musicology and information science, and particularly relates to a method for automatically judging the playing quality of a stringed musical instrument. Background technique [0002] With the rapid improvement of material living standards, people's demands for spiritual life are increasing day by day. Among them, the proportion of music art in people's spiritual life is also increasing, and instrumental music performance is the most important part of the expression of music art. Players, whether they are beginners for a few months, or players with years of playing experience, will face the problem of judging the sound quality of their performances. Because the quality of the playing quality is one of the most important basis for judging the level of the player. [0003] The factors that affect the sound quality of the performance are mainly determined by the quality of the stringed instrument itse...

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): G10L25/51G10L25/18G10L25/24
CPCG10L25/18G10L25/24G10L25/51
Inventor 管晓宏杜友田丁梦莹雷喆
Owner XI AN JIAOTONG 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
Eureka Blog
Learn More
PatSnap group products