Providing pre-computed hotword models

摘要

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.

主权项

1. A computer-implemented method comprising:
obtaining, by a server for each of multiple words or sub-words, audio data corresponding to multiple users speaking the word or sub-word; training, by the server for each of the multiple words or sub-words, a hotword model for the word or sub-word based on the audio data for the word or sub-word, wherein the hotword model for the word or sub-word is a model that is used to detect an utterance of the word or sub-word in audio input data without transcribing the word or sub-word from input audio data; storing each of the trained hotword models as a pre-computed hotword model; receiving, by the server, a candidate hotword from a computing device; identifying, by the server, one or more of the stored pre-computed hotword models that correspond to the candidate hotword; and providing, by the server, the identified, one or more of the stored pre-computed hotword models to the computing device.