Speech-to-speech translation method and device

Abstract

The invention discloses a speech-to-speech translation method. The speech-to-speech translation method comprises the steps that the corresponding relation of the content between different languages is stored in a translation reference database, and a speech-to-speech translation device obtains a source speech of a first user; the speech-to-speech translation device carries out matching on the translation reference database according to the source speech, and obtains an objective speech according to the matching result; the speech-to-speech translation device provides the objective speech for a second user. The invention further and correspondingly discloses the speech-to-speech translation device. According to the speech-to-speech translation method and device, when speech translation or text translation is carried out, matching is carried out on the translation reference database firstly, and when the objective speech corresponding to the source speech, or an objective text corresponding to a source text is stored in the translation reference database, the speech translation time can be shortened, the frequency of conversation delay can be reduced, and user experience can be improved.

Description

technical field [0001] The invention relates to the field of data transmission, in particular to a voice translation method and device. Background technique [0002] With the continuous improvement of communication technology, the continuous extension of communication network coverage area, and the popularization of communication terminal equipment, there are more and more calls between different countries. In order to solve the inconvenience caused by language differences in different countries, it is necessary to operate The vendor proposed a solution that can convert between different languages, so that the two parties using different languages ​​can communicate with each other. [0003] figure 1 It is a schematic diagram of the speech translation service application scenario. In the figure, user 1 and user 2 are respectively connected to the core network machine translation platform through the base station, and use the machine translation service. [0004] based on f...

AI Technical Summary

Problems solved by technology

[0011] Although the voice conversion during the call can be realized based on the above solution, it takes a lot of time to translate all voices in real time, which will lead to increased call delay and affect user experience

Images