Method and device for realizing voice singing

A technology of speech and speech fragments, applied in speech analysis, speech recognition, instruments, etc., can solve problems such as sound quality degradation and signal loss, and achieve the effect of avoiding loss

Active Publication Date: 2014-07-09
IFLYTEK CO LTD
View PDF11 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Obviously, there is a signal loss in the conversion from the speech signal to the feature parameter, an...

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
  • Method and device for realizing voice singing
  • Method and device for realizing voice singing
  • Method and device for realizing voice singing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Such as figure 1 A schematic flow chart of a method for singing voice provided by the embodiment of the present invention is shown.

[0041] Step 101, receiving a voice signal input by a user;

[0042] Step 102: Segment the speech signal to obtain speech fragments of each basic investigation unit; wherein, the basic investigation unit is the smallest pronunciation unit corresponding to a single note, such as a character of a Chinese song, a syllable of an English song, and the like.

[0043] Step 103, according to the preset numbered musical notation, determine the corresponding relationship between each note in the numbered musical notation and each of the basic investigation units;

[0044] Step 104, according to the pitch of each note in the numbered musical notation, and described corresponding relation, determine the target basic frequency value of its corresponding basic investigation unit respectively;

[0045] Step 105, according to the number of beats of each...

Embodiment 2

[0049] Such as figure 2 As shown in FIG. 1 , it is a schematic flow chart of a method for realizing voice-singing provided by an embodiment of the present invention.

[0050] Step S10, receiving a voice signal input by a user.

[0051] In step S11, the speech signal is divided into speech segments of basic investigation units.

[0052] In the embodiment of the present invention, the speech signal is divided into speech segments of basic investigation units, and the specific operations are as follows: image 3 shown, including:

[0053] Step S111, pre-processing the voice signal, the pre-processing operation can specifically be to perform noise reduction processing on the voice signal; specifically, it can be to perform voice enhancement on the voice segment by Wiener filtering and other technologies, so as to improve the processing capability of the subsequent system for the signal .

[0054] Step S112, extracting the speech acoustic feature vector frame by frame from the s...

Embodiment 3

[0120] Such as Figure 8 As shown, a schematic diagram of a device for realizing voice singing, the device may include: a receiving unit 801, a segmentation unit 802, an acquisition unit 803, an acquisition unit 804, an acquisition unit 805, and an adjustment unit 806 ;

[0121] a receiving unit 801, configured to receive a voice signal input by a user;

[0122] The segmentation unit 802 is configured to segment the speech signal to obtain speech segments of each basic investigation unit;

[0123] The obtaining corresponding relationship unit 803 is used to determine the corresponding relationship between each note in the numbered musical notation and each of the basic investigation units;

[0124] The obtaining fundamental frequency unit 804 is used to determine the target fundamental frequency value of the corresponding basic investigation unit according to the pitch of each note in the numbered musical notation and the corresponding relationship;

[0125] The acquisition...

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 embodiment of the invention discloses a method and device for realizing voice singing. The method includes: receiving a voice signal input by a user; segmenting the voice signal so as to obtain a voice fragment of each basic inspection unit; according to a preset numbered musical notation, determining a corresponding relation of notes in the numbered musical notation and the basic inspection units; according to the pitches of the notes in the numbered musical notation, and the corresponding relation, determining respectively target fundamental frequency values of corresponding basic inspection units; according to the beats of the notes in the numbered musical notation and the corresponding relation, determining respectively target durations of corresponding basic inspection units; and according to the target fundamental frequency values and the target durations, adjusting the voice fragments of the basic inspection units so that the adjusted fundamental frequency values of the voice fragments are equal to the target fundamental frequency value and the adjusted durations of the voice fragments are equal to the target duration. The method avoids loss of a plurality of signal conversions and realizes conversion of a voice of any length and any content into singing voice of any song.

Description

technical field [0001] The invention relates to the field of speech signal processing, in particular to a method and device for realizing singing of speech. Background technique [0002] In recent years, the singing synthesis system, that is, the method of converting the text data input by the user into singing voice, has been widely researched and applied. The realization of a singing synthesis system first requires the recording of a large amount of song data, including voice data and numbered musical notation data, in order to provide the voice fragments required by the synthesis system or to train reliable model parameters. However, due to the high cost of song data recording, the singing synthesis system can only choose to record the data of a specific speaker, and the corresponding singing synthesis effect is limited to the timbre of a specific speaker, which is not suitable for personalized customization and cannot be realized. to the interpretation of a specific sou...

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): G10L15/04G10L15/26G10L15/28
CPCG10L21/013G10H2250/455G10L2021/0135
Inventor 孙见青凌震华江源何婷婷胡国平胡郁刘庆峰
Owner IFLYTEK CO LTD
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