Voice adjusting method and system, electronic equipment and computer readable storage medium
An adjustment method and adjustment system technology, which are applied in the field of mobile communication and can solve problems such as poor call experience
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0047] A voice adjustment method such as figure 1 shown, including:
[0048] Step 10, during the call, collect voice information;
[0049] Step 20, detecting the voice information, if the voice information is noise voice, then perform step 30, if the voice information is call voice, then perform step 60;
[0050] Step 30. Obtain the noise energy of the noisy speech; specifically, detect the speech information based on a speech activation detection algorithm.
[0051] Step 40. Adjust the speech parameters of the downlink speech information received in the downlink communication link according to the noise energy; the speech parameters include volume and frequency response.
[0052] Step 50: Play the adjusted downlink voice information.
[0053] After the step of detecting the voice information, the voice adjustment method further includes:
[0054] Step 60: Send the call voice through an uplink communication link.
[0055] Take mobile phone calls as an example, see figur...
Embodiment 2
[0061] This embodiment is further improved on the basis of embodiment 1, as image 3 As shown, during the call, step 10 specifically includes:
[0062] Step 101, during the call, collect a frame of voice information every preset time period;
[0063] Further, step 20 specifically includes: step 201, detecting whether the speech information of the current frame is noise speech, and if so, performing step 301;
[0064] Step 301, obtaining the noise energy of the noise speech in the current frame;
[0065] Step 401: Adjust the speech parameters of downlink speech information in the same time period as the current frame of noise speech according to the noise energy of the current frame of noise speech, and then perform step 50.
[0066] This embodiment explains that when processing voice information, a frame of data is read every preset time, for example, in reference embodiment 1, the data volume of a frame of 20 ms is read, and then the same data as the noise voice is read. The...
Embodiment 3
[0068] A speech conditioning system such as Figure 4 As shown, the voice adjustment system includes an acquisition module 1, a detection module 2, an adjustment module 3 and a playback module 4;
[0069] The collection module 1 is used to collect voice information during a call;
[0070] The detection module 2 is used to detect the voice information, and if the voice information is noise voice, then obtain the noise energy of the noise voice; specifically, the detection module 2 is used to detect the voice activation detection algorithm based on the voice information. voice message.
[0071] The adjustment module 3 is used for adjusting voice parameters of the downlink voice information received in the downlink communication link according to the noise energy; the voice parameters include volume and frequency response.
[0072] The playing module 4 is used for playing the adjusted downlink voice information.
[0073] The voice adjustment system also includes a sending modu...
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