Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A voice processing and voice technology, which is applied in the video field, can solve the problems of TV voice recognition and privacy and security, and achieve a good communication environment and the effect of ensuring security
Inactive Publication Date: 2017-03-29
LETV HLDG BEIJING CO LTD +1
View PDF2 Cites 3 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0006] The embodiment of the present invention provides a voice processing method and device, which are used to solve the problem that the TV voice recognition and privacy security cannot be taken into account in the existing voice processing solutions in the prior art, and it is impossible to create a voice recognition system for the user in the TV. Problems facing a good communication environment
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
no. 1 example
[0027] refer to figure 1 , shows a flow chart of a speech processing method according to an embodiment of the present invention, and the method may specifically include the following steps:
[0028] Step 101, recognizing the voice sent by the user;
[0029] Among them, when the user turns on the voice recognition function of the TV, the voice recognition function of the TV can be used to recognize the voice uttered by the user. 1 set", where the user is telling others his mobile phone number, such as chatting, and then immediately speaking the voice to control the TV, then the sensitive information (such as the mobile phone number is 1352****055) will be blocked Recognized, the recognized voice data is "the mobile phone number is 1352****055, change to the central 1 set".
[0030] Step 102, performing word segmentation processing on the recognized speech data to obtain multiple word segmentations;
[0031] In order to increase the search speed for the private vocabulary in ...
no. 2 example
[0040] refer to figure 2 , which shows a flow chart of the steps of the voice processing method according to another embodiment of the present invention, which specifically includes the following steps:
[0041] Step 201, detecting the volume of the voice uttered by the user;
[0042] Wherein, in order to reduce the noise in the recognized user's voice and improve the high recognition degree of the user's voice, the volume of the user's voice may be detected first before recognizing the user's voice.
[0043] Step 202, if the volume is greater than a preset volume threshold, adjust the playback volume of the TV to within a preset volume range;
[0044] Specifically, when it is detected that the decibel of the user's speaking voice is higher than a preset volume threshold (for example, 60 decibels), the current output volume of the TV may be automatically lowered to, for example, 20-40 decibels.
[0045] Among them, the basis for setting the preset volume threshold can be re...
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
Login to view more
Abstract
The embodiment of the invention provides a voice processing method and device. The method comprises the following steps: identifying a voice made by a user; performing word segmentation processing on identified voice data to obtain a plurality of segmented words; matching the multiple segmented words with privacy words in a privacy database; shielding successfully matched segmented words to obtain target voice data; and sending the target voice data to target electronic equipment. The embodiment of the invention can first perform the word segmentation processing on the voice before execution or transmission of the voice made by the user, then match the segmented words with the privacy words to find out the privacy information in the voice of the user and shield the privacy information, and sends or executes the voice of the user after shielding the privacy words, so that a voice identification function of a television is realized, and the security of user privacy is guaranteed; and therefore, a good communication environment is created for the user in front of the television.
Description
technical field [0001] The present invention relates to the field of video technology, in particular to a voice processing method and device. Background technique [0002] With the increasing popularity of the voice recognition function, most of the high-end smart TVs currently on the market have rich voice recognition functions, so that users can control the smart TV through voice. Wherein, when performing voice control, the television needs to record, store and transmit the recognized voice of the user to a third-party electronic device for voice control. [0003] Then, for the existing voice processing solutions applied to TV sets, the following methods are mainly adopted: when voice recognition is required, the user needs to turn on the voice recognition function of the TV set, and once the voice recognition function is turned on, the user can use the Any voice uttered in front of the TV will be used as the recognized object, so as to carry out the above-mentioned recor...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more