Speech processing method, device and system, and storage medium
A voice processing and voice information technology, applied in the field of data processing, can solve the problem that the listener cannot accurately listen to the content of the speech, and achieve the effect of improving efficiency and accuracy, and enhancing signal strength
Active Publication Date: 2020-02-18
LENOVO (BEIJING) CO LTD
View PDF11 Cites 7 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] However, during the actual speaking process of the speaker, it may be affected by noise such as the ambient sound of the scene and the voices of other members, resulting in the actual output voice information containing a lot of noise, resulting in the listener being unable to accurately hear the speaker's speech content
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0054] The following will clearly and completely describe the technical solutions in the embodiments of the application with reference to the drawings in the embodiments of the application. Apparently, the described embodiments are only some of the embodiments of the application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.
[0055] It should be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings. In the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.
[0056] It should be understood that "system", "device", "unit" and / or "module" used in this application is a method for distinguishing different components, elements, parts, parts or assemblies of diffe...
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 invention provides a speech processing method, device and system, and a storage medium. In a noisy scene, after multimedia processing equipment acquires speech information including multiple pieces of speech and a human face image displayed by a video interface, the mouth area of the human face image is tracked and detected, so that corresponding mouth motion information is acquired; since thedifferent mouth motion information is often corresponding to the different speech, target speech information matched with the mouth motion information can be accordingly extracted from the multiple pieces of speech information, namely that target speech of a spokesman displayed by the video interface is extracted; and then, through enhancing signal strength of the target speech, the difference between the signal strength of the target speech information and the signal strength of the other speech information (namely noise) is increased, the output target speech information is highlighted, target speech information recognition efficiency and accuracy in the noisy scene are improved, and the condition that audiences can accurately learn speech content of the spokesman is ensured.
Description
technical field [0001] The present application mainly relates to the technical field of data processing, and more specifically relates to a voice processing method, device, system and storage medium. Background technique [0002] At present, in meetings, TV interviews, speeches and other scenarios, in order to facilitate each member to clearly see the actions and expressions of the speaker during the speech and listen to the voice information of the speaker, at least one video interface is usually configured. To display the face image of the speaker and play the voice information of the speaker at the same time. [0003] However, during the actual speaking process of the speaker, it may be affected by noise such as the ambient sound of the scene and the voices of other members, resulting in the actual output voice information containing a lot of noise, resulting in the listener being unable to accurately hear the speaker's speech content. Contents of the invention [0004...
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
Login to View More IPC IPC(8): G10L15/25G06K9/00
CPCG10L15/25G06V40/20
Inventor 张银平杨琳汪俊杰贾宸梁玉龙
Owner LENOVO (BEIJING) CO LTD