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

Audio start point detection method and device

A detection method and technology of a detection device are applied in the field of image processing, which can solve the problems of false detection and missed detection, weak sense of rhythm, etc., and achieve the effect of reducing false detection and missed detection and improving the phenomenon of signal offset.

Active Publication Date: 2021-07-20
BEIJING BYTEDANCE NETWORK TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the above algorithm is mainly suitable for audio signals with clear boundaries and relatively single rhythm (such as fast-paced music with clear note boundaries and relatively single rhythm), while for some audio signals with relatively complex rhythms and low sense of rhythm (such as multi-instrument mixed music, Music and vocals with a relatively slow rhythm), the above detection algorithm cannot accurately detect the boundary, and frequent false detections and missed detections will occur

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 start point detection method and device
  • Audio start point detection method and device
  • Audio start point detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] Figure 2a It is a flow chart of the audio onset detection method provided in Embodiment 1 of the present disclosure. The audio onset detection method provided in this embodiment can be executed by an audio onset detection device, and the audio onset detection device can be implemented as software. Or implemented as a combination of software and hardware, the audio onset detection device can be integrated in a certain device in the audio onset detection system, such as an audio onset detection server or an audio onset detection terminal device. This embodiment may be applicable to scenes of relatively complex audio with a low sense of rhythm (such as music mixed with multiple instruments, music with a relatively slow rhythm, and human voice). Such as Figure 2a As shown, the method includes the following steps:

[0049] Step S21: Determine the speech spectrum parameters corresponding to each frequency band according to the frequency domain signal corresponding to the ...

Embodiment 2

[0066] Figure 3a The flow chart of the audio start point detection method provided by Embodiment 2 of the present disclosure. On the basis of the above embodiments, this embodiment further optimizes the step of determining the start point position according to the speech spectrum parameters and mean values ​​corresponding to each frequency band. This embodiment The example can be applied to the scene of some relatively complex audio with low sense of rhythm (such as music mixed with multiple instruments, music with a relatively slow rhythm, and human voice). Such as Figure 3a shown, including:

[0067] Step S31: Determine the speech spectrum parameters corresponding to each frequency band according to the frequency domain signal corresponding to the audio signal of the audio.

[0068] Step S32: Determine the mean value of the voice spectrum parameters according to the voice spectrum parameters of the current frequency band and the voice spectrum parameters of the preset nu...

Embodiment 3

[0077] Figure 4 A schematic structural diagram of the audio onset detection device provided in Embodiment 3 of the present disclosure. The audio onset detection device can be implemented as software, or a combination of software and hardware. The audio onset detection device can be integrated and set at the audio onset In a device in the detection system, such as an audio start point detection server or an audio start point detection terminal device. This embodiment may be applicable to scenes of relatively complex audio with a low sense of rhythm (such as music mixed with multiple instruments, music with a relatively slow rhythm, and human voice). Such as Figure 4 As shown, the device includes: a parameter determination module 41, an average value determination module 42 and a starting point determination module 43; wherein,

[0078] The parameter determination module 41 is used to determine the corresponding voice spectrum parameters of each frequency band according to t...

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 disclosure discloses an audio start point detection method, device, electronic equipment and computer-readable storage medium. Wherein the audio starting point detection method comprises: for each frequency band, according to the voice spectrum parameters of the current frequency band and the voice spectrum parameters of the preset number of frequency bands selected from the remaining frequency bands, the mean value of the voice spectrum parameters is determined, wherein the remaining frequency bands are located in accordance with the time sequence All frequency bands before the current frequency band; determine one or more starting point positions of notes and syllables in the audio according to the speech spectrum parameters and mean values ​​corresponding to each frequency band. In the embodiment of the present disclosure, since the voice spectrum parameters corresponding to multiple frequency bands are referred to when determining the starting point position, the average value of the determined voice spectrum parameters is more accurate, and the signal offset in the curve formed by referring to the voice spectrum parameters and the average value is improved. phenomenon, so that the starting point of notes and syllables in the audio can be accurately detected, reducing the occurrence of false detection and missed detection.

Description

technical field [0001] The present disclosure relates to the technical field of image processing, and in particular to an audio start point detection method, device, electronic equipment, and computer-readable storage medium. Background technique [0002] Audio onset detection is an information extraction algorithm applied to audio signals, the goal is to accurately detect the onset position of notes and syllables. A note (note) specifically refers to a music signal; a syllable (phone) specifically refers to a speech human voice signal. Audio starting point detection has many important uses and application prospects in the field of signal processing, such as the following: automatic segmentation and automatic labeling of human voice and music audio, information extraction, segment compression, and interactive entertainment. Figure 1a and Figure 1b represents the starting point detection, where Figure 1a for the audio signal, Figure 1b is the detected starting point pos...

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): G10L15/05G10L19/02G10L25/87
CPCG10L15/05G10L19/02G10L25/87
Inventor 李为
Owner BEIJING BYTEDANCE NETWORK TECH 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
Eureka Blog
Learn More
PatSnap group products