Utilizing pre-event and post-event input streams to engage an automated assistant
Techniques are described herein for selectively processing a user's utterances captured prior to and after an event that invokes an automated assistant to determine the user's intent and/or any parameters required for resolving the user's intent. In various implementations, respective measures of fitness for triggering responsive action by the automated assistant may be determined for pre-event and a post-event input streams. Based on the respective measures of fitness, one or both of the pre-event input stream or post-event input stream may be selected and used to cause the automated assistant to perform one or more responsive actions.
1. A method implemented using one or more processors, comprising:
executing an automated assistant in an inactive listening state at least in part on a computing device operated by a user;
while in the inactive listening state, and prior to detecting one or more hot words that trigger transition of the automated assistant from the inactive listening state into an active listening state:
capturing, at a microphone of the computing device operated by the user, and temporarily storing in a memory buffer of the computing device operated by the user, as a pre-event input stream, first audio data containing a first utterance spoken by the user, and
capturing, at a vision sensor of the computing device operated by the user, while the user speaks the first utterance, a first set of one or more image frames;
detecting the one or more hot words in a second utterance spoken by the user subsequent to the first utterance;
subsequent to detecting the one or more hot words in the second utterance:
capturing, at the microphone as a post-event input stream, second audio data containing a third utterance spoken by the user subsequent to the second utterance;
capturing, at the vision sensor, while the user speaks the third utterance, a second set of one or more image frames;
analyzing the first and second sets of one or more image frames to identify one or more visual cues;
based on the analyzing, determining respective measures of fitness of the pre-event and post-event input streams for triggering responsive action by the automated assistant;
based on the respective measures of fitness, selecting an input stream from a set of the pre-event input stream and the post-event input stream for fulfillment by the automated assistant; and
causing the automated assistant to perform one or more responsive actions based on a command associated with the selected input stream.
2. The method of claim 1 , further comprising performing speaker recognition processing on at least a portion of the audio data captured by the microphone to determine an identity of the user, wherein the respective measures of fitness are determined further based on the speaker recognition.
3. The method of claim 2 , wherein the respective measures of fitness are determined based on the identity of the user matching an owner of the computing device.
4. The method of claim 1 , wherein the detecting is performed using a digital signal processor integral with the computing device operated by the user.
5. The method of claim 4 , wherein the digital signal processor is integral with a digital signal processing chip, and wherein the memory buffer comprises a digital signal processing buffer onboard the digital signal processing chip.
6. The method of claim 1 , wherein the memory buffer comprises a circular memory buffer that is periodically overwritten by newly captured audio data.
7. The method of claim 1 , wherein the memory buffer is configured to temporarily store audio data captured over a predetermined time interval.
8. The method of claim 1 , wherein one or more of the responsive actions comprises formulating, and submitting to a search engine, a search query that contains one or more tokens from the selected input stream;
providing output that conveys content responsive to the search query.
9. The method of claim 1 , wherein one or more of the responsive actions comprises operating a smart appliance.
10. A system comprising one or more processors and memory storing instructions that, in response to execution of the instructions by the one or more processors, cause the one or more processors to perform the following operations:
execute an automated assistant in an inactive listening state at least in part on a computing device operated by a user;
while in the inactive listening state, and prior to detecting one or more hot words that trigger transition of the automated assistant from the inactive listening state into an active listening state:
capture, at a microphone of the computing device operated by the user, and temporarily storing in a memory buffer of the computing device operated by the user, as a pre-event input stream, first audio data containing a first utterance spoken by the user, and
capture, at a vision sensor of the computing device operated by the user, while the user speaks the first utterance, a first set of one or more image frames;
detect the one or more hot words in a second utterance spoken by the user subsequent to the first utterance;
subsequent to detection of the one or more hot words in the second utterance:
capture, at the microphone as a post-event input stream, second audio data containing a third utterance spoken by the user subsequent to the second utterance;
capture, at the vision sensor, while the user speaks the third utterance, a second set of one or more image frames;
analyze the first and second sets of one or more image frames to identify one or more visual cues;
based on the identified one or more visual cues, determine respective measures of fitness of the pre-event and post-event input streams for triggering responsive action by the automated assistant;
based on the respective measures of fitness, select an input stream from a set of the pre-event input stream and the post-event input stream for fulfillment by the automated assistant; and
cause the automated assistant to perform one or more responsive actions based on a command associated with the selected input stream.
11. The system of claim 10 , further comprising instructions to perform speaker recognition processing on at least a portion of the audio data captured by the microphone to determine an identity of the user, wherein the respective measures of fitness are determined further based on the speaker recognition.
12. The system of claim 11 , wherein the respective measures of fitness are determined based on the identity of the user matching an owner of the computing device.
13. The system of claim 10 , wherein the one or more hot words are detected using a digital signal processor integral with the computing device operated by the user.
14. The system of claim 13 , wherein the digital signal processor is integral with a digital signal processing chip, and wherein the memory buffer comprises a digital signal processing buffer onboard the digital signal processing chip.
15. The system of claim 10 , wherein the memory buffer comprises a circular memory buffer that is periodically overwritten by newly captured audio data.
16. The system of claim 10 , wherein the memory buffer is configured to temporarily store audio data captured over a predetermined time interval.
17. At least one non-transitory computer-readable medium comprising instructions that, in response to execution of the instructions by one or more processors, cause the one or more processors to perform the following operations:
execute an automated assistant in an inactive listening state at least in part on a computing device operated by a user;
while in the inactive listening state, and prior to detecting one or more hot words that trigger transition of the automated assistant from the inactive listening state into an active listening state:
capture, at a microphone of the computing device operated by the user, and temporarily storing in a memory buffer of the computing device operated by the user, as a pre-event input stream, first audio data containing a first utterance spoken by the user, and
capture, at a vision sensor of the computing device operated by the user, while the user speaks the first utterance, a first set of one or more image frames;
detect the one or more hot words in a second utterance spoken by the user subsequent to the first utterance;
subsequent to detection of the one or more hot words in the second utterance:
capture, at the microphone as a post-event input stream, second audio data containing a third utterance spoken by the user subsequent to the second utterance;
capture, at the vision sensor, while the user speaks the third utterance, a second set of one or more image frames;
analyze the first and second sets of one or more image frames to identify one or more visual cues;
based on the identified one or more visual cues, determine respective measures of fitness of the pre-event and post-event input streams for triggering responsive action by the automated assistant;
based on the respective measures of fitness, select an input stream from a set of the pre-event input stream and the post-event input stream for fulfillment by the automated assistant; and
cause the automated assistant to perform one or more responsive actions based on a command associated with the selected input stream.
18. The at least one non-transitory computer-readable medium of claim 17 , further comprising instructions to perform speaker recognition processing on at least a portion of the audio data captured by the microphone to determine an identity of the user, wherein the respective measures of fitness are determined further based on the speaker recognition.
19. The at least one non-transitory computer-readable medium of claim 18 , wherein the respective measures of fitness are determined based on the identity of the user matching an owner of the computing device.
20. The at least one non-transitory computer-readable medium of claim 17 , wherein the one or more hot words are detected using a digital signal processor integral with the computing device operated by the user.