Method for processing voice signals and terminal thereof

A method for processing a voice signal, applicable to a server, the method comprising:

• receiving a plurality of second data packets from a terminal, wherein each of the plurality of second data packets carries a sequence identifier, wherein the terminal is mounted with a live streaming application;
• splicing the plurality of second data packets according to sequences identified by the sequence identifiers carried by the plurality of second data packets to acquire a first voice signal;
• generating an acknowledgement result in response to determining that the first voice signal comprises a preset wake-up word, wherein the acknowledgement result is intended to indicate that the server determines that the first voice signal comprises the preset wake-up word;
• and
• sending the acknowledgement result to the terminal,
• to cause the terminal to:
• respond to, after receiving the acknowledgment result, an interaction instruction corresponding to a received second voice signal in a live streaming room, to implement a function in the live streaming room that a user needs to execute, wherein the function is a function of the live streaming application and comprises a photographing function, a microphone-connecting function, a music-playing function, or a gift-giving function.

A terminal on which a live streaming application is mounted, comprising:

• a processor, and
• a memory configured to store a computer program;
• wherein the computer program, when executed by the processor, causes the processor to perform a method comprising:
• receiving a first voice signal when an interaction interface of a live streaming room is in a display state, wherein the live streaming room is configured fora real-time video behavior,
• sending the first voice signal to a server in response to determining that the first voice signal comprises a preset wake-up word;
• receiving a second voice signal in response to receiving an acknowledgement result from the server, wherein the acknowledgement result is intended to indicate that the server determines that the first voice signal comprises the preset wake-up word;
• and
• responding to an interaction instruction corresponding to the second voice signal in the live streaming room, to implement a function in the live streaming room that a user needs to execute, wherein the function is a function of the live streaming application and comprises a photographing function, a microphone-connecting function, a music-playing function, or a gift-giving function.