Providing pre-computed hotword models
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, for each of multiple words or sub-words, audio data corresponding to multiple users speaking the word or sub-word; training, for each of the multiple words or sub-words, a pre-computed hotword model for the word or sub-word based on the audio data for the word or sub-word; receiving a candidate hotword from a computing device; identifying one or more pre-computed hotword models that correspond to the candidate hotword; and providing the identified, pre-computed hotword models to the computing device.
1. A computer-implemented method comprising:
providing a first graphical user interface on a display of a computing device, wherein the first graphical user interface includes a prompt requesting that a user associates a user-provided hotword with an action;
providing, in response to detecting a user-provided utterance in which the user associates a user-provided hotword with an action, a second graphical user interface on the display of the computing device, wherein the second graphical user interface includes a display of the proposed transcription of the detected user-provided utterance; and
providing, in response to a confirmation that the proposed transcription is correct, a third graphical user interface on the display of the computing device, wherein the third graphical user interface includes a confirmation display of the transcription of the detected utterance.
2. The computer-implemented method of claim 1 , wherein the third graphical user interface includes text indicating that the user has confirmed that the proposed transcription of the detected user-provided utterance is correct.
3. The computer-implemented method of claim 1 , further comprising:
allowing the user-provided hotword associated with the action to be used in further communication with the computing device.
4. The computer-implemented method of claim 3 , wherein allowing the user-provided hotword associated with the action to be used in further communication with the computing device comprises:
allowing the user-provided hotword to initiate the action, associated with the user-provided hotword, on the computing device.
5. The computer-implemented method of claim 1 , wherein the first graphical user interface includes text indicating to the user to provide a hotword.
6. The computer-implemented method of claim 1 , wherein the second graphical user interface includes text requesting the user to confirm, or reject, the proposed transcription of the detected user-provided utterance.
7. The computer-implemented method of claim 6 , wherein the second graphical user interface further includes selectable buttons that the user is able to select to indicate whether to confirm or reject the proposed transcription.
8. A system comprising:
one or more computers; and
one or more storage devices storing instructions that are operable, when executed by one or more computers, to cause the one or more computers to perform operations comprising:
providing a first graphical user interface on a display of a computing device, wherein the first graphical user interface includes a prompt requesting that a user associates a user-provided hotword with an action;
providing, in response to detecting a user-provided utterance in which the user associates a user-provided hotword with an action, a second graphical user interface on the display of the computing device, wherein the second graphical user interface includes a display of the proposed transcription of the detected user-provided utterance; and
providing, in response to a confirmation that the proposed transcription is correct, a third graphical user interface on the display of the computing device, wherein the third graphical user interface includes a confirmation display of the transcription of the detected utterance.
9. The system of claim 8 , wherein the third graphical user interface includes text indicating that the user has confirmed that the proposed transcription of the detected user-provided utterance is correct.
10. The system of claim 8 , wherein the operations further comprise:
allowing the user-provided hotword associated with the action to be used in further communication with the computing device.
11. The system of claim 10 , wherein allowing the user-provided hotword associated with the action to be used in further communication with the computing device comprises:
allowing the user-provided hotword to initiate the action, associated with the user-provided hotword, on the computing device.
12. The system of claim 8 , wherein the first graphical user interface includes text indicating to the user to provide a hotword.
13. The system of claim 8 , wherein the second graphical user interface includes text requesting the user to confirm, or reject, the proposed transcription of the detected user-provided utterance.
14. The system of claim 13 , wherein the second graphical user interface further includes selectable buttons that the user is able to select to indicate whether to confirm or reject the proposed transcription.
15. One or more non-transitory computer-readable storage mediums comprising instructions stored thereon that are executable by a processing device and upon such execution cause the processing device to perform operations comprising:
providing a first graphical user interface on a display of a computing device, wherein the first graphical user interface includes a prompt requesting that a user associates a user-provided hotword with an action;
providing, in response to detecting a user-provided utterance in which the user associates a user-provided hotword with an action, a second graphical user interface on the display of the computing device, wherein the second graphical user interface includes a display of the proposed transcription of the detected user-provided utterance; and
providing, in response to a confirmation that the proposed transcription is correct, a third graphical user interface on the display of the computing device, wherein the third graphical user interface includes a confirmation display of the transcription of the detected utterance.
16. The non-transitory computer-readable storage medium of claim 15 , wherein the third graphical user interface includes text indicating that the user has confirmed that the proposed transcription of the detected user-provided utterance is correct.
17. The non-transitory computer-readable storage medium of claim 15 , wherein the operations further comprise:
allowing the user-provided hotword associated with the action to be used in further communication with the computing device.
18. The non-transitory computer-readable storage medium of claim 17 , wherein allowing the user-provided hotword associated with the action to be used in further communication with the computing device comprises:
allowing the user-provided hotword to initiate the action, associated with the user-provided hotword, on the computing device.
19. The non-transitory computer-readable storage medium of claim 15 , wherein the first graphical user interface includes text indicating to the user to provide a hotword.
20. The non-transitory computer-readable storage medium of claim 15 , wherein the second graphical user interface includes text requesting the user to confirm, or reject, the proposed transcription of the detected user-provided utterance.
21. The non-transitory computer-readable storage medium of claim 20 , wherein the second graphical user interface further includes selectable buttons that the user is able to select to indicate whether to confirm or reject the proposed transcription.