Attention-based dynamic audio level adjustment

摘要

In one example, a technique may include outputting, by a computing device associated with a user and for playback at a first volume level by an audio output device, first audio data, receiving, by the computing device, audio input data, and responsive to determining, by the computing device, that the audio input data includes speech associated with an entity different from the user, determining, by the computing device and based at least in part on the audio input data, whether to output second audio data. The method may also include, responsive to determining to output the second audio data: determining, by the computing device, a second volume level lower than the first volume level, and outputting, by the computing device and for playback at the second volume level by the audio output device, the second audio data.

主权项

1. A method comprising:
outputting, by a computing device associated with a user, for playback by an audio output device at a first volume level, first audio output data; receiving, by the computing device, audio input data; responsive to determining, by the computing device, that the audio input data includes speech associated with an entity different from the user and that the speech includes a conversational keyword, determining, by the computing device and based at least in part on the audio input data, whether to output second audio output data; and responsive to determining to output the second audio output data:
determining, by the computing device, a second volume level lower than the first volume level; andoutputting, by the computing device, for playback by the audio output device at the second volume level, the second audio output data.