Controlling device output according to a determined condition of a user
Dynamically controlling output from a device, such as an automated assistant device. Control of the output can be based on, for example, a condition and/or physiological attribute(s) of a user of the device. Various implementations dynamically control the output to improve sleep quality for the user and/or mitigate waste of computational and/or network resources.
1. A method, implemented by one or more processors of an assistant computing device, comprising:
in response to detecting an occurrence of an invocation at the assistant computing device:
transitioning the assistant computing device from a first state to a second state, wherein in the first state the assistant computing device does not perform certain processing of audio data detected via one or more microphones of the assistant computing device, and wherein in the second state the assistant computing device performs the certain processing of audio data detected via the one or more microphones;
responsive to transitioning the assistant computing device to the second state, and for a duration of the second state:
rendering ambient audio via one or more speakers of the assistant computing device, wherein the rendering is for the duration of the second state in which the assistant computing device performs the certain processing of audio data, and wherein the duration of the second state begins with transitioning the assistant computing device from the first state to the second state, in which the automated assistant performs the certain processing of audio data, and wherein the duration of the second state ends with the cessation of the second state; and
responsive to cessation of the second state:
ceasing the rendering of the ambient audio.
2. The method of claim 1 , further comprising:
when in the first state:
monitoring for occurrence of an invocation phrase by processing audio data detected via the one or more microphones using only a local invocation model stored locally at the assistant computing device,
wherein transitioning the assistant computing device from the first state to the second state is based on detecting the occurrence of the invocation phrase in a portion of the audio data.
3. The method of claim 1 , further comprising:
when in the first state:
monitoring for occurrence of an invocation gesture by processing video data detected via one or more cameras of the assistant computing device,
wherein transitioning the assistant computing device from the first state to the second state is based on detecting the occurrence of the invocation gesture in a portion of the video data.
4. The method of claim 1 , further comprising:
selecting the ambient audio based on the ambient audio being stored in association with a user profile that is determined based at least in part on further analysis of the portion of the audio data.
5. The method of claim 1 , further comprising:
determining a volume for the rendering of the ambient audio, wherein rendering the ambient audio is at the determined volume.
6. The method of claim 5 , wherein determining the volume is based on one or more of:
a level of background noise as detected via the one or more microphones, an estimated distance of an active user of the assistant computing device, or one or more physiological characteristics of the active user.
7. The method of claim 1 , wherein the certain processing comprises one or more of:
transmitting the audio data to a remote automated assistant server and/or speech-to-text processing.
8. The method of claim 1 , wherein, in the first state:
rendering a response that is responsive to a previous request received via the assistant device, and wherein transitioning the assistant computing device from the first state to the second state occurs automatically in response to completion of rendering the response.
9. A method, implemented by one or more processors of an assistant computing device, comprising:
monitoring for occurrence of an invocation phrase by processing audio data detected via the one or more microphones;
in response to detecting the invocation phrase in a portion of the audio data:
rendering ambient audio via one or more speakers of the assistant computing device;
performing, while rendering the ambient audio, certain processing, of audio data detected via the one or more microphones, that is not performed prior to detecting the invocation phrase, wherein the certain processing includes processing a request that is included in the audio data, and wherein performing the certain processing of the audio data begins when rendering the ambient audio begins and ends when rendering the ambient audio ends; and
rendering a response that is responsive to the request; and
in response to starting rendering of the response:
ceasing the rendering of the ambient audio.
10. The method of claim 9 , wherein monitoring for occurrence of the invocation phrase by processing audio data detected via the one or more microphones includes using only a local invocation model stored locally at the assistant computing device.
11. The method of claim 9 , wherein the certain processing comprises speech-to-text processing.
12. The method of claim 9 , further comprising:
processing the audio data to determine a user profile for a user that uttered the invocation phrase; and
selecting the ambient audio based on the ambient audio being stored in association with the user profile.
13. The method of claim 9 , further comprising:
determining a volume for the rendering of the ambient audio, wherein rendering the ambient audio is at the determined volume.
14. The method of claim 13 , wherein determining the volume is based on one or more of:
a level of background noise as detected via the one or more microphones, an estimated distance of an active user of the assistant computing device, or one or more physiological characteristics of the active user.
15. An assistant computing device, comprising one or more processors, and memory configured to store instructions that, when executed by one or more of the processors, cause one or more of the processors to perform operations that include:
in response to detecting an occurrence of an invocation at the assistant computing device:
transitioning the assistant computing device from a first state to a second state, wherein in the first state the assistant computing device does not perform certain processing of audio data detected via one or more microphones of the assistant computing device, and wherein in the second state the assistant computing device performs the certain processing of audio data detected via the one or more microphones;
responsive to transitioning the assistant computing device to the second state, and for a duration of the second state:
rendering ambient audio via one or more speakers of the assistant computing device, wherein the rendering is for the duration of the second state in which the assistant computing device performs the certain processing of audio data, and wherein the duration of the second state begins with transitioning the assistant computing device from the first state to the second state, in which the automated assistant performs the certain processing of audio data, and wherein the duration of the second state ends with the cessation of the second state; and
responsive to cessation of the second state:
ceasing the rendering of the ambient audio.
16. The computing device of claim 15 , wherein the operations further include:
when in the first state:
monitoring for occurrence of an invocation phrase by processing audio data detected via the one or more microphones using only a local invocation model stored locally at the assistant computing device,
wherein transitioning the assistant computing device from the first state to the second state is based on detecting the occurrence of the invocation phrase in a portion of the audio data.
17. The computing device of claim 15 , wherein the operations further include:
selecting the ambient audio based on the ambient audio being stored in association with a user profile that is determined based at least in part on further analysis of the portion of the audio data.
18. The computing device of claim 15 , wherein the operations further include:
determining a volume for the rendering of the ambient audio, wherein rendering the ambient audio is at the determined volume.
19. The computing device of claim 18 , wherein determining the volume is based on one or more of:
a level of background noise as detected via the one or more microphones, an estimated distance of an active user of the assistant computing device, or one or more physiological characteristics of the active user.
20. The computing device of claim 15 , wherein the certain processing comprises one or more of:
transmitting the audio data to a remote automated assistant server, or speech-to-text processing.