System and method for stably recording speaking in seminar
A seminar and stable technology, applied in the parts of the TV system, the parts and instruments of the color TV, etc., can solve the problem that the speech information is difficult to be recorded stably, and achieve the effect of reducing crosstalk and noise interference
Pending Publication Date: 2022-05-31
杭州云嘉云计算有限公司
View PDF1 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] The present invention mainly solves the problem that the speech information of the seminar is difficult to be stably recorded in the existing technology; it provides a system and method for stably recording the speech of the seminar
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
[0031] Example: A system for stably recording speeches in a seminar, such as figure 1 As shown, it includes a sound acquisition module 1, an image acquisition module 2, a sound source signal preprocessing module 3, a sound source gain module 4, a noise identification module 5, a crosstalk identification module 6, an image processing module 7 and an audio output module 8. The processing module is connected with the sound acquisition module, the sound source gain module is connected with the sound source signal preprocessing module, the noise identification module is connected with the sound source gain module, the crosstalk identification module is connected with the noise identification module, and the image processing module is connected with the crosstalk identification module and the image acquisition module respectively. The modules are connected, and the audio output module is respectively connected with the image processing module and the crosstalk identification module. ...
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 discloses a system and method for stably recording speaking in a seminar, and the system comprises sound collection modules which are distributed at a seminar site, divide each sound collection module into a collection region, and are connected with a processing module; the image acquisition module is used for acquiring image information of personnel on a seminar site and is connected with the processing module; the processing module is used for carrying out noise and crosstalk processing on the sound source information to obtain a stable sound source signal, matching a spokesman with a sound source according to the processed sound source signal and the personnel image information and then outputting the sound source; according to the invention, the sound collection module is used for carrying out regional sound source signal collection on a seminar, the image collection module is combined to carry out speaking person image collection, the processing module carries out sound source gain, noise identification and crosstalk identification processing on the collected information to obtain stable sound source information, and stable sound source output is carried out after the stable sound source information is matched with a spokesman. Stable recording of speaking of a seminar is achieved, and crosstalk and noise interference are reduced.
Description
technical field [0001] The present invention relates to the technical field of sound signal processing, in particular to a system and method for stably recording speeches in a seminar. Background technique [0002] The currently applied speech recognition system has many prerequisites to ensure high recognition accuracy, the most important of which include 1) the speaker's speech is stable and clear, and can be collected smoothly by the pickup device; 2) the speaker speaks one by one, and it is easy for multiple people to speak at the same time In case of wrong recognition results, the most common error phenomenon is that the recognition results of other people's speech appear on the self-recognition interface; 3) The recorded scene environment is relatively quiet, with less white noise and a uniform radio environment. At present, there are two main strategies to optimize the above phenomenon: [0003] First, adjust the hardware facilities of each site and limit the distanc...
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 Patent Type & Authority Applications(China)
IPC IPC(8): G10L21/0272G10L21/0308G10L21/0264G10L21/02G10L25/30H04R1/08H04N5/232
CPCG10L21/0272G10L21/0308G10L21/0264G10L21/02G10L25/30H04R1/083H04R2201/02H04N23/695
Inventor 麦联韬唐海江朱宇袁宇豪
Owner 杭州云嘉云计算有限公司