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 method comprising:
receiving, at data processing hardware, from a user device, text corresponding to a personalized term for initiating the user device to perform a particular action, the user device configured to:
receive, in a graphical user interface executing on the user device, an input indication corresponding to a user entering the text corresponding to the personalized term; and
send the text corresponding to the personalized term to the data processing hardware;
receiving, at the data processing hardware, from the user device, audio data corresponding to an utterance spoken by the user; and
when the personalized term is detected in the utterance spoken by the user, initiating, by the data processing hardware, the user device to perform the particular action.
2. The method of claim 1 , wherein the user device is further configured to, prior to receiving the input indication in the graphical user interface, display a prompt in the graphical user interface, the prompt requesting the user to provide the personalized term.
3. The method of claim 1 , further comprising, prior to receiving the audio data corresponding to the utterance spoken by the user, obtaining, by the data processing hardware, using the text corresponding to the personalized term, a detection model that corresponds to the personalized term.
4. The method of claim 3 , further comprising detecting, by the data processing hardware, using the obtained detection model, the personalized term in the audio data corresponding to the utterance spoken by the user.
5. The method of claim 3 , wherein obtaining the detection model comprises dynamically creating the detection model based on the received text corresponding to the personalized term.
6. The method of claim 3 , wherein obtaining the detection model comprises retrieving the detection model that corresponds to the personalized term from a vocabulary database.
7. The method of claim 6 , further comprising storing, by the data processing hardware, the detection model in the vocabulary database prior to receiving the text corresponding to personalized term.
8. The method of claim 3 , wherein the detection model is trained based on portions of audio samples of other users speaking other words that are not the personalized term.
9. The method of claim 1 , wherein the personalized term comprises two or more words.
10. The method of claim 1 , wherein the personalized term comprises a single word.
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, from a user device, text corresponding to a personalized term for initiating the user device to perform a particular action, the user device configured to:
receive, in a graphical user interface executing on the user device, an input indication corresponding to a user entering the text corresponding to the personalized term; and
send the text corresponding to the personalized term to the data processing hardware;
receiving, from the user device, audio data corresponding to an utterance spoken by the user; and
when the personalized term is detected in the utterance spoken by the user, initiating the user device to perform the particular action.
12. The system of claim 11 , wherein the user device is further configured to, prior to receiving the input indication in the graphical user interface, display a prompt in the graphical user interface, the prompt requesting the user to provide the personalized term.
13. The system of claim 11 , wherein the operations further comprise, prior to receiving the audio data corresponding to the utterance spoken by the user, obtaining, using the text corresponding to the personalized term, a detection model that corresponds to the personalized term.
14. The system of claim 13 , wherein the operations further comprise detecting, using the obtained detection model, the personalized term in the audio data corresponding to the utterance spoken by the user.
15. The system of claim 13 , wherein obtaining the detection model comprises dynamically creating the detection model based on the received text corresponding to the personalized term.
16. The system of claim 13 , wherein obtaining the detection model comprises retrieving the detection model that corresponds to the personalized term from a vocabulary database.
17. The system of claim 16 , wherein the operations further comprise storing the detection model in the vocabulary database prior to receiving the text corresponding to personalized term.
18. The system of claim 13 , wherein the detection model is trained based on portions of audio samples of other users speaking other words that are not the personalized term.
19. The system of claim 11 , wherein the personalized term comprises two or more words.
20. The system of claim 11 , wherein the personalized term comprises a single word.