Audio translation method and system

Abstract

Provided are an audio translation method and system. A terminal device can send a translation service request to a central node, and the central node sends the feature information of at least one candidate edge node to the terminal device based on the translation service request. The terminal device determines a target edge node based on the feature information of each candidate edge node, and then sends translation configuration information and a to-be-translated audio stream to the target edge node. The target edge node translates the to-be-translated audio stream based on the translation configuration information to obtain a translation result, and sends the translation result of the to-be-translated audio stream to the terminal device. The center node is responsible for distributing the edge nodes to the terminal device without providing translation service, so that the load of the center node can be effectively reduced. Each edge node only needs to provide translation service fora small number of terminal devices, so that the load of the edge nodes can be effectively prevented from being too high, and the edge node has the condition of providing the translation service in real time.

Description

technical field [0001] The present application relates to the technology of speech translation, in particular, to an audio translation method and system. Background technique [0002] The types and quantities of existing video programs are becoming more and more abundant. However, most video programs are often filmed and broadcast in local mainstream languages. Even multilingual video programs generally only support a few common languages. On the one hand, for video distributors, there are huge language differences in different countries and regions. Due to cost and technical limitations, it is impossible to provide special translations for each language, and usually only provide video versions in several common languages; On the other hand, due to bandwidth limitations, generally only several video versions in common languages ​​can be selected for playback. [0003] Due to the above restrictions, video publishers are unable to release video programs to a wider market, lim...

AI Technical Summary

Problems solved by technology

[0002] The types and quantities of existing video programs are becoming more and more abundant. However, most video programs are often filmed and broadcast in the local mainstream language. Even multilingual video programs generally only support a few common languages.

On the one hand, for video distributors, there are huge language differences in different countries and regions. Due to cost and technical limitations, it is impossible to provide special translations for each language, and usually only provide video versions in several common languages; On the other hand, due to bandwidth limitations, generally only a few video versions in common languages ​​can be selected for playback.

[0003] Due to the above restrictions, video distributors are unable to release video programs to a broader market, limiting the audience of video programs, and also causing viewers to be unable to understand video programs in other languages ​​due to language limitations

The existing technology that uses conventional cloud servers to provide translation services cannot provide users with real-time translation services due to the performance and real-time defects of the cloud server itself, and when the cloud server receives a large number of translation service requests, It is easy to cause a huge impact on the cloud server, resulting in an excessive load on the cloud server

Images