Providing pre-computed hotword models
AssigneeGoogle Inc.
InventorMatthew Sharifi
Life of this patent
Estimating the term…
Abstract
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.
Claims20
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.
A system comprising:
- one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations 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.
A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations 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.
Dependencies are inferred from the claim text.