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

Method and device for preventing misrecognition of voice commands

A speech recognition and misrecognition technology, which is applied in the field of data processing, can solve problems such as rising equipment power consumption and difficulties in transplanting speech recognition algorithms, and achieve the effects of increasing complexity, increasing complexity, and reducing speech misrecognition

Active Publication Date: 2019-07-16
GUANGZHOU SHIYUAN ELECTRONICS CO LTD
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The disadvantages of the existing technology are: increasing the computing burden of the CPU leads to an increase in power consumption of the device, difficulty in transplanting speech recognition algorithms, and the possibility of false triggering cannot be fundamentally avoided

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 preventing misrecognition of voice commands
  • Method and device for preventing misrecognition of voice commands
  • Method and device for preventing misrecognition of voice commands

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0070] figure 1 This is a flow chart of a method for preventing misrecognition of voice commands provided in the first embodiment of the present invention. The method of this embodiment can be executed by a device for preventing voice misrecognition, which can be implemented by hardware and / or software, and Generally, it can be integrated in a device that has a voice command control function and can play audio files, such as mobile phones, cars, etc. The method of this embodiment specifically includes:

[0071] Step 110: Obtain a lyrics file matching the song to be played.

[0072] Generally speaking, in the prior art, devices that have both the voice command control function and the audio file playback function will directly play the audio file when it obtains the command to play the audio file, instead of reducing the size before playing. Misrecognition of voice commands caused by playing songs.

[0073] In this embodiment, before playing the song to be played, a lyric file match...

Embodiment 2

[0089] figure 2 It is a flowchart of a method for preventing misrecognition of voice commands provided by the second embodiment of the present invention. This embodiment is optimized based on the above-mentioned embodiment. In this embodiment, the lyrics file is optimized into a Chinese lyrics file;

[0090] Optimize the preset voice control commands into Chinese voice control commands;

[0091] Correspondingly, the search for false trigger phrases in the lyrics file is optimized to: traverse the pronunciation attributes of all Chinese lyrics in the Chinese lyrics file, where the pronunciation attributes include at least pitch, initials, and finals; if there is one Chinese character or one in all Chinese lyrics Each Chinese character in the Chinese character phrase has the same pronunciation attribute as the Chinese character at the corresponding position in the Chinese voice control command, then confirm that the Chinese character or Chinese character phrase is the same as the la...

Embodiment 3

[0128] image 3 It is a flowchart of a method for preventing misrecognition of voice commands provided by the third embodiment of the present invention. This embodiment is optimized on the basis of the above-mentioned embodiment. In this embodiment, the calculation of the first start time and the first end time of the phrase easy to be triggered by mistake according to the lyric file is optimized as follows: According to the lyrics file, the easy to be triggered The second start time and second end time of the playback of the lyrics sentence to which the phrase belongs; the first compensation time of the first start time and the second compensation time of the first end time are acquired; according to the second start time and second end time , The first compensation time, the second compensation time, the number of lyric units contained in the lyric sentence, the number of lyric units contained in the mis-triggered phrase, and the position of the mis-triggered phrase in the lyr...

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

A method and device for preventing misrecognition of a voice command, the method comprising: obtaining a lyrics file matching a song to be played (S110); searching for a phrase that may easily be mistriggered in the lyrics file (S120); computing, according to the lyrics file, a first start time and a first end time of the playback of the phrase that may easily be mistriggered (S130); playing the song to be played, disabling a voice recognition module when the first start time is reached, and enabling the voice recognition module when the first end time is reached (S140). The present invention overcomes the technical defects of increased computational load of a processor, increased power consumption of a device, and the difficulty in the porting of a voice recognition algorithm due to increased complexity of a voice recognition algorithm caused by the purpose of reducing voice mistriggering probability, and can also reliably reduce voice misrecognitions caused by the playback of a song without increasing the complexity of a voice recognition algorithm.

Description

Technical field [0001] The embodiments of the present invention relate to data processing technology, and in particular to a method and device for preventing misrecognition of voice commands. Background technique [0002] With the continuous development of science and technology, and people's continuous higher pursuit of quality of life, more and more devices have voice control functions. [0003] Most cars, home appliances, and mobile phones will be equipped with voice control functions. These devices can also play audio files such as songs and cross talks. When these devices are playing audio files, the voice control function may be turned on by mistake, causing the device to perform Wrong action. In the prior art, the complexity of the speech recognition algorithm is improved, the speech recognition algorithm is optimized, and the probability of false triggering is reduced. [0004] The disadvantages of the prior art are: increasing the computational burden of the CPU leads to a...

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): G10L15/22G10L15/26
CPCG10L15/22G10L15/26
Inventor 宋夏
Owner GUANGZHOU SHIYUAN ELECTRONICS CO LTD