Wake suppression for audio playing and listening devices
A system and method are disclosed for ignoring a wakeword received at a speech-enabled listening device when it is determined the wakeword is reproduced audio from an audio-playing device. Determination can be by detecting audio distortions, by an ignore flag sent locally between an audio-playing device and speech-enabled device, by and ignore flag sent from a server, by comparison of received audio played audio to a wakeword within an audio-playing device or a speech-enabled device, and other means.
1. A speech-enabled device having a connection to an audio-playing device, the speech-enabled device configured to listen for a wakeword, the speech-enabled device comprising:
a computing system comprising one or more processors and a main memory, the one or more processors configured to execute software code to:
receive audio, including the wakeword, from the audio-playing device,
analyze the received audio to spot the wakeword, and
ignore the wakeword spotted in the received audio, to leave the speech-enabled device in an idle state, upon determining the received audio came from the audio-playing device;
wherein the speech-enabled device receives the received audio at a first time from the audio-playing device via the connection and at a second time from the audio-playing device via the microphone; and
wherein the speech-enabled device is able to determine the received audio received at the second time comes from the audio-playing device by spotting the wakeword in the received audio at the first and second times and given a proximity of the first and second times.
2. The speech-enabled device of claim 1 , wherein the received audio analyzed by the processor comprises an audio stream received via the connection.
3. The speech-enabled device of claim 1 , wherein the connection is a local connection between the speech-enabled device and the audio-playing device.
4. The speech-enabled device of claim 1 , wherein the connection is a wide area connection connecting the speech-enabled device and the audio-playing device to each other and the Internet.
5. The speech-enabled device of claim 1 , wherein the speech-enabled device and the audio-playing device are part of a single device, and wherein the connection comprises electrical connections within the single device.
6. A speech-enabled device configured to listen for a wakeword, comprising:
a microphone configured to receive audio; and
means for ignoring the wakeword received at the microphone, to leave the speech-enabled device in an idle state, upon determining the received audio is reproduced audio, said means for ignoring a wakeword comprising analyzing the received audio for characteristics of reproduced audio and ignoring the wakeword where it is determined the received audio includes the characteristics of reproduced audio.
7. A speech-enabled device having a connection to an audio-playing device, the speech-enabled device configured to listen for a wakeword, the speech-enabled device comprising:
a computing system comprising one or more processors and a main memory, the one or more processors configured to execute software code to:
receive audio, including the wakeword, from the audio-playing device,
analyze the received audio to spot the wakeword, and
ignore the wakeword spotted in the received audio, to leave the speech-enabled device in an idle state, upon determining the received audio came from the audio-playing device;
wherein the speech-enabled device receives the received audio at a first time from the audio-playing device via the connection and at a second time from the audio-playing device via the microphone; and
wherein the speech-enabled device is able to determine the received audio received at the second time comes from the audio-playing device by storing a segment of the received audio received at the first time and comparing it to the received audio received at the second time.