Abstract: Described are systems, methods, and apparatus that detect keywords in one or more speech segments to authenticate that the speech is generated by the speaker as part of an intentional enrollment by the speaker into a service. For example, as a speech segment is received as part of an enrollment process, the speech segment may be converted into a log melspectrogram and the log melspectrogram may be processed using a machine learning model to determine if an expected keyword is represented by the log melspectrogram. If the keyword is detected, it may be determined that the speech output by the speaker is output as part of an intentional enrollment process.

Abstract: Disclosed are systems and methods for determining sentiment data representative of an emotional state of a user during an interaction with one or more non-users. The disclosed implementations may further determine, for frequent interactions between the user and a non-user, the identity of the non-user and provide information to the user relating to the sentiment of the user when interacting with the non-user.