Unlock instant, AI-driven research and patent intelligence for your innovation.

Energy threshold adjustment method, device and equipment and medium

A technology of energy threshold and adjustment method, which is applied in speech analysis, speech recognition, instruments, etc., can solve the problem that the energy double-threshold endpoint detection method cannot accurately collect valid speech segments, and achieve accurate collection and reduce workload.

Active Publication Date: 2020-08-14
ZHEJIANG DAHUA TECH CO LTD
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The embodiment of the present invention provides an energy threshold adjustment method, which is used to solve the technical problem that the existing energy double-threshold endpoint detection method cannot accurately collect effective speech segments

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
  • Energy threshold adjustment method, device and equipment and medium
  • Energy threshold adjustment method, device and equipment and medium
  • Energy threshold adjustment method, device and equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] figure 1 A schematic diagram of the first energy threshold adjustment process provided by the embodiment of the present invention, the process includes the following steps:

[0049] S101: Acquire energy information of an audio segment.

[0050] The energy threshold adjustment method provided by the embodiment of the present invention is used to adjust the highest energy threshold and the lowest energy threshold adopted by the energy double-threshold endpoint detection method.

[0051]In the embodiment of the present invention, obtaining the energy information of the audio segment includes calculating the short-term energy of each audio frame in the audio segment, and then obtaining the highest energy value, the lowest energy value, and the average energy value of the audio segment, etc. at least one of energy information. Specifically, the existing method for calculating the short-term energy of an audio frame can be used to calculate the energy information of the aud...

Embodiment 2

[0062] In order to accurately determine the adjusted target energy threshold, on the basis of the above embodiments, in the embodiment of the present invention, according to whether the energy fluctuation amplitude is greater than the preset fluctuation threshold, determining the adjusted target energy threshold includes:

[0063] If the energy fluctuation amplitude is greater than the preset fluctuation threshold, then determine that the highest energy threshold and the lowest energy threshold corresponding to the energy double-threshold endpoint detection method are the target energy thresholds for adjustment;

[0064] If the energy fluctuation range is not greater than the preset fluctuation threshold, the target energy threshold for adjustment is determined according to the comparison result between the energy information and the highest energy threshold and the lowest energy threshold corresponding to the energy double-threshold endpoint detection method.

[0065] In the e...

Embodiment 3

[0068] In order to accurately adjust the target energy threshold, on the basis of the above embodiments, in the embodiment of the present invention, if the highest energy threshold and the lowest energy threshold corresponding to the energy double-threshold endpoint detection method are determined as the target energy threshold for adjustment, the The adjustment to the target energy threshold includes:

[0069] Determine the adjusted highest energy threshold according to the first weight value corresponding to the second initial value of the highest energy threshold and the second weight value corresponding to the currently saved highest energy threshold;

[0070] The adjusted minimum energy threshold is determined according to the third weight value corresponding to the first initial value of the minimum energy threshold and the fourth weight value corresponding to the currently saved minimum energy threshold.

[0071] Specifically, in the embodiment of the present invention,...

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 energy threshold adjustment method, device and equipment and a medium, and solves the technical problem that an existing energy double-threshold endpoint detection method cannot accurately collect effective voice segments. According to the invention, the energy information of the audio segment is obtained, according to the energy information of the audio segment, the adjusted target energy threshold value is determined, and then the target energy threshold value is adjusted, so that the energy threshold value can be adjusted in time according to the difference of theenergy information of the audio segment, the effective voice segment can be collected more accurately, and the workload of subsequent instruction word recognition is reduced.

Description

technical field [0001] The present invention relates to the field of speech recognition, in particular to an energy threshold adjustment method, device, equipment and medium. Background technique [0002] Voice accounts for 70% of the way users interact and plays a big role in users' lives. With the advancement of science and technology, intelligent voice products are gradually integrated into daily life. Intelligent voice products include: terminal equipment, smart home and vehicle information system, etc. Users can control intelligent voice products through voice, which greatly facilitates users life. [0003] At present, when intelligent voice products recognize the user's voice, they can first collect audio segments, and then use speech recognition methods to identify whether the collected audio segments contain preset command words. If so, they will match the corresponding control words according to the command words. instruction. The following is the procedure for o...

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 Applications(China)
IPC IPC(8): G10L15/05G10L25/03G10L25/78
CPCG10L15/05G10L25/03G10L25/78G10L2025/783
Inventor 王为陆金刚方伟
Owner ZHEJIANG DAHUA TECH CO LTD