Detecting near matches to a hotword or phrase

1. A method implemented by one or more processors, the method comprising:

receiving, via one or more microphones of a client device, first audio data that captures a first spoken utterance of a user;

processing the first audio data using one or more machine learning models to generate a first predicted output that indicates a probability of one or more hotwords being present in the first audio data;

determining that the first predicted output satisfies a secondary threshold that is less indicative of the one or more hotwords being present in audio data than is a primary threshold but does not satisfy the primary threshold;

receiving, via the one or more microphones of the client device, second audio data that captures a second spoken utterance of a user;

processing the second audio data using the one or more machine learning models to generate a second predicted output that indicates a probability of the one or more hotwords being present in the second audio data;

determining that the second predicted output satisfies the secondary threshold but does not satisfy the primary threshold;

in response to the first predicted output and the second predicted output satisfying the secondary threshold but not satisfying the primary threshold, and in response to the first spoken utterance and the second spoken utterance satisfying one or more temporal criteria relative to one another, identifying a failed hotword attempt; and

in response to identifying the failed hotword attempt:

determining an intended hotword corresponding to the failed hotword attempt;

providing a hint that is responsive to the failed hotword attempt, comprising displaying the intended hotword on a display of the client device or providing, by the client device, an audio response that includes the intended hotword; and

adding a new hotword to a set of supported hotwords, the new hotword being a word or a phrase included in both the first audio data and the second audio data, wherein:

prior to adding the new hotword to the set of supported hotwords, the new hotword was active in a different context but not active in a current context; and

adding the new hotword to the set of supported hotwords comprises making the new hotword active in the current context.

2. The method according to claim 1 , wherein identifying the failed hotword attempt is further in response to determining that a similarity between the first spoken utterance and the second spoken utterance exceeds a similarity threshold.

3. The method according to claim 1 , wherein identifying the failed hotword attempt is further in response to determining that the probability indicated by the first predicted output and the probability indicated by the second predicted output correspond to a same hotword of the one or more hotwords.

4. The method according to claim 1 , further comprising determining, using a model conditioned on acoustic features, that the first audio data and the second audio data comprise a command,

wherein identifying the failed hotword attempt is further in response to the first audio data and the second audio data comprising the command.

5. The method according to claim 1 , wherein the intended hotword is determined based on acoustic similarity between at least a portion of the first audio data, at least a portion of the second audio data, and the intended hotword.

6. The method according to claim 1 , further comprising performing an action corresponding to the intended hotword.

7. The method according to claim 1 , wherein the intended hotword is determined based on semantic similarity between the intended hotword and text generated based on at least a portion of the first audio data or based on at least a portion of the second audio data.

8. The method according to claim 1 , wherein the different context comprises a first set of running applications and the current context comprises a second set of running applications.

9. The method according to claim 1 , wherein the different context comprises a first time of day and the current context comprises a second time of day.

10. The method according to claim 1 , wherein identifying the failed hotword attempt is further in response to determining that the first audio data and the second audio data are acoustically similar.

11. The method according to claim 1 , wherein neither the intended hotword nor another supported hotword is included in the first spoken utterance and the second spoken utterance.

12. A computer program product comprising one or more non-transitory computer-readable storage media having program instructions collectively stored on the one or more non-transitory computer-readable storage media, the program instructions executable to:

receive, via one or more microphones of a client device, first audio data that captures a first spoken utterance of a user;

process the first audio data using each of a plurality of classes in a machine learning model to generate a corresponding probability associated with the first audio data, each of the classes being associated with a corresponding hotword of a plurality of hotwords and each of the corresponding probabilities being associated with a probability of the corresponding hotword being present in the first audio data;

determine that the probability of one of the plurality of hotwords being present in the first audio data satisfies a secondary threshold that is less indicative of the one of the plurality of hotwords being present in audio data than is a primary threshold but does not satisfy the primary threshold;

receive, via the one or more microphones of the client device, second audio data that captures a second spoken utterance of a user;

process the second audio data using each of the plurality of classes in the machine learning model to generate a corresponding probability associated with the second audio data, each of the corresponding probabilities being associated with a probability of the corresponding hotword being present in the second audio data;

determine that the probability of the one of the plurality of hotwords being present in the second audio data satisfies the secondary threshold but does not satisfy the primary threshold;

in response to the probability of the one of the plurality of hotwords being present in the first audio data satisfying the secondary threshold but not satisfying the primary threshold and the probability of the one of the plurality of hotwords being present in the second audio data satisfying the secondary threshold but not satisfying the primary threshold, and in response to the first spoken utterance and the second spoken utterance satisfying one or more temporal criteria relative to one another, identify a failed hotword attempt; and

in response to identifying the failed hotword attempt:

determine an intended hotword corresponding to the failed hotword attempt;

provide a hint that is responsive to the failed hotword attempt, comprising displaying the intended hotword on a display of the client device or providing, by the client device, an audio response that includes the intended hotword; and

add a new hotword to a set of supported hotwords, the new hotword being a word or a phrase included in both the first audio data and the second audio data, wherein:

prior to adding the new hotword to the set of supported hotwords, the new hotword was active in a different context but not active in a current context; and

adding the new hotword to the set of supported hotwords comprises making the new hotword active in the current context.

13. The computer program product according to claim 12 , wherein identifying the failed hotword attempt is further in response to determining that a similarity between the first spoken utterance and the second spoken utterance exceeds a similarity threshold.

14. The computer program product according to claim 12 , wherein:

the program instructions are further executable to determine, using a model conditioned on acoustic features, that the first audio data and the second audio data comprise a command; and

identifying the failed hotword attempt is further in response to the first audio data and the second audio data comprising the command.

15. The computer program product according to claim 12 , wherein the intended hotword is determined based on acoustic similarity between at least a portion of the first audio data, at least a portion of the second audio data, and the intended hotword.

16. The computer program product according to claim 12 , wherein the program instructions are further executable to perform an action corresponding to the intended hotword.

17. A system comprising:

a processor, a computer-readable memory, one or more computer-readable storage media, and program instructions collectively stored on the one or more computer-readable storage media, the program instructions executable to:

receive, via one or more microphones of a client device, first audio data that captures a first spoken utterance of a user;

process the first audio data using one or more machine learning models to generate a first predicted output that indicates a probability of one or more hotwords being present in the first audio data;

determine that the first predicted output satisfies a secondary threshold that is less indicative of the one or more hotwords being present in audio data than is a primary threshold but does not satisfy the primary threshold;

receive, via the one or more microphones of the client device, second audio data that captures a second spoken utterance of a user;

process the second audio data using the one or more machine learning models to generate a second predicted output that indicates a probability of the one or more hotwords being present in the second audio data;

determine that the second predicted output satisfies the secondary threshold but does not satisfy the primary threshold;

in response to the first predicted output and the second predicted output satisfying the secondary threshold but not satisfying the primary threshold, and in response to the first spoken utterance and the second spoken utterance satisfying one or more temporal criteria relative to one another, identify a failed hotword attempt; and

in response to identifying the failed hotword attempt:

determine an intended hotword corresponding to the failed hotword attempt;

perform an action based on the failed hotword attempt, comprising displaying the intended hotword on a display of the client device or providing, by the client device, an audio response that includes the intended hotword; and

add a new hotword to a set of supported hotwords, the new hotword being a word or a phrase included in both the first audio data and the second audio data, wherein:

prior to adding the new hotword to the set of supported hotwords, the new hotword was active in a different context but not active in a current context; and

adding the new hotword to the set of supported hotwords comprises making the new hotword active in the current context.

18. The system according to claim 17 , wherein:

the program instructions are further executable to determine, using a model conditioned on acoustic features, that the first audio data and the second audio data comprise a command; and

identifying the failed hotword attempt is further in response to (i) the first audio data and the second audio data comprising the command and (ii) determining that a similarity between the first spoken utterance and the second spoken utterance exceeds a similarity threshold.

19. The system according to claim 17 , wherein identifying the failed hotword attempt is further in response to determining that the probability indicated by the first predicted output and the probability indicated by the second predicted output correspond to a same hotword of the one or more hotwords.