Meeting recording method, apparatus and device and computer readable medium
A conference record and conference technology, applied in speech analysis, speech recognition, instruments, etc., to achieve the effect of saving resources, improving accuracy, and improving work efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0054] see figure 1 , which is a flow chart of the steps of the conference record method in Embodiment 1 of the present invention. Embodiment 1 provides a conference record method, including the following steps:
[0055] S110: Preprocessing the conference voice.
[0056] In a general meeting, due to the influence of the surrounding environment, different noises will be generated. Therefore, it is necessary to preprocess the voice information in the meeting to improve the accuracy of voice recognition. Such as figure 2 As shown, in an embodiment, the step S110 includes:
[0057] S111: Perform echo cancellation processing.
[0058] In general conferencing systems, especially in remote conferencing systems, acoustic echo often occurs, that is, the sound played by the speaker is picked up by the microphone and sent back to the far end, so that the far end talker can hear his own voice. Therefore, echo cancellation processing is required. For example, an echo cancellation me...
Embodiment 2
[0070] The difference from Embodiment 1 is that this Embodiment 2 also adds a trigger step, and the specific scheme is as follows:
[0071] Such as image 3 As shown, the second embodiment provides a conference record method, including the following steps:
[0072] S210: Preprocessing the conference voice.
[0073] S220: When a trigger signal is received, execute step S230.
[0074] By adding a trigger step, it is convenient for the user to activate and deactivate the voice conversion function at any time. Wherein, the form of triggering may be: button triggering, that is, by setting a trigger button, the user can manually trigger the voice conversion function. It can also be adopted: keyword triggering, that is, the user triggers the voice conversion function by saying a certain keyword.
[0075] S230: Perform sentence segmentation on the conference voice, and upload it to the voice server for text conversion.
[0076] S240: Receive text information converted from voice ...
Embodiment 3
[0079] The third embodiment corresponds to the first embodiment, and provides a conference recording device. see Figure 4 , which is a connection block diagram of the conference recording device in the third embodiment.
[0080] The meeting recording device of the third embodiment includes:
[0081] The preprocessing module 110 is configured to preprocess the conference voice. Wherein, the preprocessing module 110 includes: an echo cancellation unit 111 , a beamforming unit 112 , a noise reduction unit 113 and an enhancement amplification unit 114 .
[0082] The echo cancellation unit 111 is configured to perform echo cancellation processing.
[0083] The beamforming unit 112 is configured to perform beamforming processing on the conference voice. The beamforming unit 112 includes:
[0084] The voice information receiving subunit 112a is configured to receive conference voice information through the microphone array.
[0085] The weighted summation subunit 112b is confi...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com