A method and device for online speech translation
A technology for voice translation and voice information, applied in the field of online translation, it can solve problems such as poor communication, errors, and inability to communicate across languages, and achieve the effect of improving accuracy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0053] figure 1 It is a flow chart of an online speech translation method provided by Embodiment 1 of the present invention. This embodiment can be applied to the situation of speech recognition and translation when both parties conduct cross-language speech communication. The method can be executed by an online speech translation device, which can be implemented by hardware and / or software, and the device can be configured in any In the terminal or network element. The method specifically includes the following:
[0054] S101. Perform voice recognition on first voice information input by a first user to obtain first identification information.
[0055] In the above operation, the first user and the second user communicate across languages, the first user can use the first voice to input the first voice information, and the online voice translation device can perform voice recognition on it to obtain the first identification information.
[0056] S102. Prompt the first user...
Embodiment 2
[0070] figure 2 It is a flowchart of an online speech translation method provided by Embodiment 2 of the present invention. In the actual process of communication between the two parties, the dialogue content is generated based on certain dialogue scenarios and dialogue rules. Therefore, on the basis of Embodiment 1 of the present invention, Embodiment 2 of the present invention optimizes the online speech translation process based on dialogue scenarios and dialogue rules. The online speech translation method provided in this embodiment includes:
[0071] S201. Perform voice recognition on first voice information input by a first user to obtain first identification information.
[0072] S202. Determine the current dialogue scene according to the first identification information, or identify the current dialogue scene according to keywords in the historical identification information confirmed by the first user;
[0073] In the above operations, some dialogue scenarios and t...
Embodiment 3
[0083] image 3 It is a flow chart of an online speech translation method provided by Embodiment 3 of the present invention. Based on the above-mentioned embodiments of the present invention, this embodiment provides a preferred implementation of an online speech translation method, taking the first user as a Chinese user and the second user as a French user for example. The method includes:
[0084] S301. The first user uses Chinese to input "the train ticket from Nice to Paris this afternoon" through the microphone as the first voice information, conducts voice recognition on it, and obtains the first recognition information. Due to various reasons such as accent and environmental noise, The identification information may be "Jingtian train ticket to Paris from 14 in the afternoon".
[0085] S302. Determine the confidence level of "Jingtian train ticket from 14 to Paris in the afternoon". If the confidence level is lower than the set threshold value, execute S303; otherwis...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 