Hotword-Based Speaker Recognition

A system comprising:

• data processing hardware;
• and
• memory hardware in communication with the data processing hardware and storing instructions that when executed on the data processing hardware cause the data processing hardware to perform operations comprising:
• for each of a plurality of different users in a multi-user environment sharing a voice-based authentication device:
• receiving audio features of a hotword spoken by the corresponding user in one or more user-identification utterances captured by a microphone of the voice-based authentication device;
• and
• associating the audio features of the hotword spoken by the corresponding user with a corresponding user name for the corresponding user;
• receiving a first utterance spoken by one of the plurality of different users in the multi-user environment, the first utterance captured by the voice-based authentication device and comprising the hotword and a query;
• establishing an identity of the user that spoke the first utterance based on audio features of the portion of the first utterance that corresponds to the hotword;
• based on the established identify of the user that spoke the first utterance, processing the query following the hotword in the first utterance to identify an operation to perform that requires access to one personal resource of an associated set of personal resources for the user that spoke the first utterance;
• and
• accessing the required one of the personal resources of the associated set of personal resources for the user that spoke the first utterance to perform the identified operation.