Identifying people that are proximate to a mobile device user via social graphs, speech models, and user context

摘要

Techniques are provided to improve identification of a person using speaker recognition. In one embodiment, a unique social graph may be associated with each of a plurality of defined contexts. The social graph may indicate speakers likely to be present in a particular context. Thus, an audio signal including a speech signal may be collected and processed. A context may be inferred, and a corresponding social graph may be identified. A set of potential speakers may be determined based on the social graph. The processed signal may then be compared to a restricted set of speech models, each speech model being associated with a potential speaker. By limiting the set of potential speakers, speakers may be more accurately identified.

主权项

1. A method for identifying a speaker with a mobile device, the method comprising:
capturing, via a microphone on the mobile device, audio data comprising a speech signal; inferring, via the mobile device, a context of a user of the mobile device; identifying, via the mobile device, a social graph based at least partly on the inferred context, the social graph comprising a list of potential speakers; and identifying, via the mobile device, a speaker determined to have vocally contributed to the speech signal, the speaker identification based at least partly on the identified social graph.