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

Audio content correction method and intelligent device thereof

A content and audio technology, applied in the field of audio processing, can solve the problem of inability to correct audio information files

Inactive Publication Date: 2018-07-06
北京小唱科技有限公司
View PDF9 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main purpose of this application is to provide a method for correcting audio content and its smart device to solve the technical problem that the audio information files cannot be correctly corrected due to the randomization of the syllable time interval of the lyrics sung by people.

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
  • Audio content correction method and intelligent device thereof
  • Audio content correction method and intelligent device thereof
  • Audio content correction method and intelligent device thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0085] First, collect the audio information sung by the user, wherein the audio information refers to the original human voice without sound processing, and then perform rhythm analysis on the audio information through speech recognition technology, wherein the rhythm analysis refers to the Each lyric syllable in the original audio information is confirmed, and the time node of each lyric syllable is marked on a singing time axis, so as to obtain a set of data containing each lyric syllable and its corresponding time node information, namely is the rhythm feature of the original audio information, in other embodiments of the present application, it is also possible to segment the audio information and perform feature extraction on each segment to obtain the features of all segments in the audio information to which it belongs, by The feature makes all the segments correspond to a segment in the template, wherein the time mapping relationship between the audio information segmen...

Embodiment 2

[0091]First, collect the audio information sung by the user, wherein the audio information refers to the original human voice without sound processing, and then perform rhythm analysis on the audio information through speech recognition technology, wherein the rhythm analysis refers to the Each lyric syllable in the original audio information is confirmed, and the time node of each lyric syllable is marked on a singing time axis, so as to obtain a set of data containing each lyric syllable and its corresponding time node information, namely is the rhythm feature of the original audio information.

[0092] Then, load the rhythm standard comparison template, wherein, the rhythm standard comparison template is bound to the singing accompaniment, downloaded to the local synchronously, and does not need to request data from the cloud again when the audio information is corrected, the rhythm standard comparison template It is extracted from the standard audio information matched wit...

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 an audio content correction method and an audio content correction intelligent device. The audio content correction method comprises the steps of: acquiring audio information sung by a user, performing fundamental frequency analysis on the audio information to obtain fundamental frequency features, and performing rhythm analysis on the audio information to obtain rhythm features, comparing the rhythm features with a template to obtain a time offset sequence, comparing the fundamental frequency features with a template according to the time offset sequence so as to obtain a pitch difference sequence, and performing tone modulation and speed change processing on the audio information of the user according to the time offset sequence and the pitch difference sequence to obtain a corrected audio. By correcting the rhythm and pitch separately, the technical problem that the rhythm and pitch on a timeline interfere with each other and cannot be accurately corrected inoverall analysis in the related art is solved.

Description

technical field [0001] The invention relates to the technical field of audio processing, in particular to a method for modifying audio content and an intelligent device thereof. Background technique [0002] In people's daily life, singing songs is a kind of entertainment that the public likes very much. However, because different people have different levels of professionalism in music, they often appear out of tune and out of tune during the singing process. It is necessary to correct the singing audio in the later stage. [0003] When the related technology corrects the audio information, it converts the audio information as a whole and then analyzes it. However, since the audio information sung by people has the characteristics of randomization of the interval between syllables in the lyrics, it is impossible to compare the pitch at the correct time point with the pitch corresponding to the correct template after comparison, and the audio information cannot be correctly...

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): G10L21/007
CPCG10L21/007
Inventor 王国腾
Owner 北京小唱科技有限公司
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