Method and apparatus for activating application by speech input

An apparatus comprising:

• a memory;
• and
• one or more processors coupled to the memory, the one or more processors configured to:
• receive an input sound stream including an activation keyword for activating a target application and a speech command portion that follows the activation keyword;
• detect the activation keyword from the input sound stream;
• process the speech command portion to determine whether to activate the target application;
• generate sensor data indicative of an environment where the device is located using one or more context sensors in the apparatus;
• and
• selectively activate the target application based on the processing of the speech command and the sensor data.

A method for processing input sound, the method comprising:

• receiving, at an electronic device, a first input sound stream including an activation keyword for activating a target application and a first speech command portion that follows the activation keyword;
• detecting, at the electronic device, the activation keyword from the first input sound stream;
• processing the first speech command portion to determine whether to activate the target application;
• generating sensor data indicative of an environment where the device is located using one or more context sensors;
• responsive to determining, based on the processing of the first speech command portion, that the target application is not to be activated, detecting the activation keyword from a second input sound stream that further includes a second speech command portion;
• processing the second speech command portion to determine whether to activate the target application;
• and
• activating the target application based on the processing of the second speech command portion and the sensor data.

An apparatus comprising:

• a memory;
• and
• one or more processors coupled to the memory, the one or more processors configured to:
• receive a first input sound stream including an activation keyword for activating a target application and a first speech command portion that follows the activation keyword;
• detect the activation keyword from the first input sound stream;
• process the first speech command portion to determine whether to activate the target application;
• generating sensor data indicative of an environment where the device is located using one or more context sensors in the electronic device;
• and
• responsive to a determination, based on the processing of the first speech command portion, that the target application is not to be activated, detect the activation keyword from a second input sound stream that further includes a second speech command portion;
• process the second speech command portion to determine whether to activate the target application;
• and
• activate the target application based on the processing of the second speech command portion and the sensor data.