Speech recognition method and device
A technology of speech recognition and recognition results, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of general recognition accuracy, network quality influence, and limited CPU processing capacity, and achieve the effect of improving accuracy and flexibility
Active Publication Date: 2018-04-10
GD MIDEA AIR-CONDITIONING EQUIP CO LTD
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Offline recognition does not need to be transmitted through the network, so the response speed is fast, but due to the influence of the CPU performance of the device, the CPU processing capacity is limited, and the recognition engine algorithm is relatively simple, so the recognition accuracy is average. The online recognition engine runs on the cloud server and can use the cloud The powerful processing capability of the server runs a more complex recognition engine algorithm, thereby greatly improving the recognition accuracy, but affected by the quality of the network, the limitations are relatively high
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
[0037] It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
[0038] The invention provides a voice recognition method.
[0039] refer to figure 1 , figure 1 It is a schematic flowchart of a preferred embodiment of the speech recognition method of the present invention.
[0040] The present embodiment proposes a speech recognition method, and the speech recognition method includes the following steps:
[0041] Step S10, when the voice signal is received and the current network status is normal, send the received voice signal to a preset recognition server for recognition, and obtain the recognition result fed back by the recognition server;
[0042] In this embodiment, when the voice signal is received, the current network status can be judged, and if the terminal has connected to the network and can communicate normally, it can be judged that the current network status is no...
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 speech recognition method. The speech recognition method includes the following steps that when a speech signal is received and the current network state is normal, the received speech signal is transmitted to a preset recognition server to be recognized, and recognition results which are fed back by the recognition server are acquired; home terminal recognition is conducted on the received speech signal, and the recognition results are acquired; recognition accuracy degrees corresponding to the recognition results are calculated; the recognition result which has the highest recognition accuracy degree and is fed back by the recognition server is used as the recognition result of the speed signal. The invention further discloses a speech recognition device. According to the speech recognition method and device, the speed recognition accuracy is guaranteed, and meanwhile the speed recognition flexibility is improved.
Description
technical field [0001] The invention relates to the field of voice control, in particular to a voice recognition method and device. Background technique [0002] Traditional household appliances use remote controls and panel buttons for human-computer interaction. Voice recognition technology enables machines to be remotely controlled by voice, and using voice to control terminals has become a new way of human-computer interaction. Terminal speech recognition includes two methods. The first method is offline recognition, that is, the recognition engine is embedded in the local CPU, and the recognition algorithm is run on the local CPU, which is called offline recognition; the second is cloud recognition. Run the recognition engine on the cloud server, the terminal device connects to the cloud server through the network, sends the received audio signal to the cloud server, and the cloud server returns the recognition result to the terminal. This kind of recognition is called ...
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 Patents(China)
IPC IPC(8): G10L15/30
Inventor 何伟旭
Owner GD MIDEA AIR-CONDITIONING EQUIP CO LTD