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 when executed on data processing hardware causes the data processing hardware to perform operations comprising:
receiving a candidate hotword from a user device, the candidate hotword input by a user of the user device via a graphical user interface executing on the user device;
identifying, from multiple waveforms stored on memory hardware in communication with the data processing hardware, a matching waveform associated with the candidate hotword;
based on the identified matching waveform, dynamically creating a hotword model that corresponds to the candidate hotword; and
transmitting the dynamically created hotword model to the user device.
2. The computer-implemented method of claim 1 , wherein the graphical user interface executing on the user device is configured to display a prompt requesting the user to provide the candidate hotword.
3. The computer-implemented method of claim 1 , wherein the graphical user interface executing on the user device is configured to display text corresponding to the candidate hotword.
4. The computer-implemented method of claim 3 , wherein the operations further comprise receiving a user input indication indicating that the user accepts the text corresponding to the candidate hotword displayed in the graphical user interface.
5. The computer-implemented method of claim 1 , wherein the candidate hotword comprises one word.
6. The computer-implemented method of claim 1 , wherein the candidate hotword comprises two or more words.
7. The computer-implemented method of claim 1 , wherein the candidate hotword is input by the user as a text-based input via the graphical user interface.
8. The computer-implemented method of claim 1 , wherein the user inputs the candidate hotword by speaking the candidate hotword.
9. The computer-implemented method of claim 1 , wherein the hotword model comprises a neural network.
10. The computer-implemented method of claim 1 , wherein the dynamically created hotword model is configured to detect the candidate hotword in spoken utterances.
11. A system comprising:
data processing hardware; and
memory hardware in communication with the data processing hardware and storing instructions that when executed by the data processing hardware cause the data processing hardware to perform operations comprising:
receiving a candidate hotword from a user device, the candidate hotword input by a user of the user device via a graphical user interface executing on the user device;
identifying, from multiple waveforms stored on the memory, a matching waveform associated with the candidate hotword;
based on the identified matching waveform, dynamically creating a hotword model that corresponds to the candidate hotword; and
transmitting the dynamically created hotword model to the user device.
12. The system of claim 11 , wherein the graphical user interface executing on the user device is configured to display a prompt requesting the user to provide the candidate hotword.
13. The system of claim 11 , wherein the graphical user interface executing on the user device is configured to display text corresponding to the candidate hotword.
14. The system of claim 13 , wherein the operations further comprise receiving a user input indication indicating that the user accepts the text corresponding to the candidate hotword displayed in the graphical user interface.
15. The system of claim 11 , wherein the candidate hotword comprises one word.
16. The system of claim 11 , wherein the candidate hotword comprises two or more words.
17. The system of claim 11 , wherein the candidate hotword is input by the user as a text-based input via the graphical user interface.
18. The system of claim 11 , wherein the user inputs the candidate hotword by speaking the candidate hotword.
19. The system of claim 11 , wherein the hotword model comprises a neural network.
20. The system of claim 11 , wherein the dynamically created hotword model is configured to detect the candidate hotword in spoken utterances.