Genius button secondary commands

摘要

Methods, systems and articles for receiving, by a telecommunication device, audio input through a unified audio interface are disclosed herein. The telecommunication device is further configured to perform at least one of a dictation action, an incoming message processing action, a navigation action, a content lookup action, or a contact lookup action while continuously or substantially continuously receiving voice commands from a user. In some aspects, the telecommunications device may continuously receive and process voice command while operating in a driving mode, which may be initiated by the telecommunications device.

主权项

1. A method implemented in a telecommunication device, the method comprising:
receiving a text-based message; audibly announcing a name of a contact associated with the received text-based message; receiving, via an audio recognition module, a continuous string of audio input from a user through a unified audio interface of the telecommunication device; performing, via the audio recognition module, a text translation of the audio input received from the user of the telecommunication device; analyzing, via an audio routing module, at least a portion of the continuous string of audio input from the text translation to determine to handle the audio input as at least one of a process of the telecommunication device, a request of a telecommunication device application, or a network search request; determining, via the audio routing module, that the audio input is associated with a command to perform an action that is understood by the telecommunication device or the telecommunication device application; identifying, via the audio routing module, the action as a dictation action that is associated with the received text message; initiating, via the audio routing module, the dictation action while continuing to receive the continuous string of audio input from the user; and performing, via the audio routing module, the dictation action by generating text via a voice-to-text conversion of at least part of the continuous string of audio input received from the user.