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

Music separation method of MFCC (Mel Frequency Cepstrum Coefficient)-multi-repetition model in combination with HPSS (Harmonic/Percussive Sound Separation)

A music and background music technology, applied in speech analysis, electroacoustic musical instruments, instruments, etc., can solve the problems of poor music separation adaptability

Inactive Publication Date: 2015-05-13
CHONGQING UNIV OF POSTS & TELECOMM
View PDF3 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the separation method based on repeated features has only been developed. For different types of sound sources, the adaptability of music separation using repeated structures is still poor, and more exploration and research are needed.

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
  • Music separation method of MFCC (Mel Frequency Cepstrum Coefficient)-multi-repetition model in combination with HPSS (Harmonic/Percussive Sound Separation)
  • Music separation method of MFCC (Mel Frequency Cepstrum Coefficient)-multi-repetition model in combination with HPSS (Harmonic/Percussive Sound Separation)
  • Music separation method of MFCC (Mel Frequency Cepstrum Coefficient)-multi-repetition model in combination with HPSS (Harmonic/Percussive Sound Separation)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] As mentioned above, the traditional repetitive structure separation method is easy to miss the music information with a relatively gentle rhythm, because the extraction of the repetitive structure adopts the "rhythm spectrum" method, which is easy to capture the sound source information with obvious rhythm changes, but It is easy to miss the more soothing sound sources produced by orchestral instruments (such as flute, violin, piano, etc.). In this regard, the harmonic source separation is added before the separation. Here, the harmonic and impact source separation method HPSS is used to analyze the sound source first, and then separate it, so as to effectively improve the separation performance.

[0028] Generally speaking, the spectrogram of a music signal usually presents two forms of distribution, one is a continuous and smooth distribution along the time axis, and the other is a continuous and smooth distribution along the frequency axis. The sound sources of these ...

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 music separation method of an MFCC (Mel Frequency Cepstrum Coefficient)-multi-repetition model in combination with an HPSS (High Performance Storage System), and relates to the technical field of signal processing. In consideration of high probability of ignore of a gentle sound source and time-varying change characteristic of music, the sound source type is analyzed through a harmonic / percussive sound separation (HPSS) method to separate out a harmonic source, then MFCC characteristic parameters of the remaining sound sources are extracted, and similar operation is performed on the sound sources to construct a similar matrix so as to establish a multi-repetition structural model of the sound source suitable for tune transformation, so that a mask matrix is obtained, and finally the time domain waveform of a song and background music is obtained through ideal binary mask (IBM) and fourier inversion. According to the method, effective separation can be performed on different types of sound source signals, so the separation precision is improved; meanwhile the method is low in complexity, high in processing speed and higher in stability, and has broad application prospect in the fields such as singer retrieval, song retrieval, melody extraction and voice recognition in a musical instrument background.

Description

Technical field: [0001] The invention relates to audio signal processing, in particular to the separation of singing voice and background music in music signals. Background technique [0002] Extracting the background music and singing voice of music has broad application prospects in the field of audio signal processing, such as singer retrieval and song retrieval, melody extraction, speech recognition in the background of musical instruments, etc., but audio separation is also a very challenging task. On the problem of polyphonic music separation, the auditory system of the human ear has an incredible ability. People can easily distinguish the singing voice in the music from the background music, and even distinguish which instruments are included in the tune. These are easy things, but For computers, however, there are many difficulties. [0003] Today's music separation techniques are mainly statistical techniques and research techniques based on psychoacoustics. Stati...

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): G10L21/028G10L25/81
CPCG10H1/00G10H2210/041G10H2210/056G10H2250/235G10L25/81
Inventor 张天骐徐昕张刚高超阳锐李灿
Owner CHONGQING UNIV OF POSTS & TELECOMM
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com