Method and apparatus for language detection based voice real-time translation as a service in telecom

A network node, comprising:

• at least one memory configured to store computer program code;
• and
• at least one processor configured to access said at least one memory and operate as instructed by the computer program code, the computer program code including:
• receiving code configured to cause at least one of said at least one processor to receive at least one data packet associated with a voice call, the at least one data packet including (i) header information that specifies a source address and a destination address and (ii) voice data;
• performing code configured to cause at least one of said at least one processor to, in response to determining the at least one data packet is associated with a subscriber of a translation service performed in the network node, perform the translation service including:
• (i) detecting a first language of the voice data of the at least one data packet, by analyzing the voice data included in the at least one data packet in order to automatically detect the first language;
• (ii) translating the voice data to a second language specified by the subscriber in response to a determination the second language is different than the first language;
• and
• (iii) transmitting the at least one data packet with the translated voice data to the destination address,
• wherein the voice data of the received at least one data packet contains source speech, the translation service further includes detecting voice characteristics of the source speech of the voice data, and the translating the voice data to the second language is further based on the detected voice characteristics such that the translated voice data sounds as if spoken by a speaker of the source speech of the voice data.

A non-transitory computer readable medium having instructions stored therein, which when executed by a processor in a network node cause the processor to execute a method comprising:

• receiving, by the network node of a telecommunications network, at least one data packet associated with a voice call, the at least one data packet including (i) header information that specifies a source address and a destination address and (ii) voice data;
• in response to determining the at least one data packet is associated with a subscriber of a translation service performed in the network node, performing the translation service including:
• (i) detecting, by the network node, a first language of the voice data of the at least one data packet, the network node analyzing the voice data included in the at least one data packet in order to automatically detect the first language;
• (ii) translating, by the network node, the voice data to a second language specified by the subscriber in response to a determination the second language is different than the first language;
• and
• (iii) transmitting, by the network node, the at least one data packet with the translated voice data to the destination address,
• wherein the voice data of the received at least one data packet contains source speech, the translation service further includes detecting voice characteristics of the source speech of the voice data, and the translating the voice data to the second language is further based on the detected voice characteristics such that the translated voice data sounds as if spoken by a speaker of the source speech of the voice data.