Real-time speaker state analytics platform

A system for providing speech-derived speaker state data, the system comprising:

• a speech data processing subsystem embodied in one or more non-transitory machine accessible storage media, the speech data processing subsystem configured to produce speech data corresponding to a variable-length time window of audio input captured from a human or synthetic speaker;
• a plurality of analytics engines embodied in one or more non-transitory machine accessible storage media, wherein an analytics engine of the plurality of analytics engines is configured to analyze speech data produced by the speech data processing subsystem and provide as output speaker state data, the plurality of analytics engines comprising
• a plurality of algorithms configured for different types of speaker state analytics, at least one of the plurality of algorithms analyzing at least one non-word feature of the speech data and outputting speaker state data relating to a type of speaker state analytics for which the at least one of the plurality of algorithms has been configured;
• wherein the speech data processing subsystem is configured to use the variable-length time window to determine and output the speaker state data, the speaker state data aligned with time and indicative of at least one correlation between the speech data and at least one short-term measurement of a speaker state analytic and at least one correlation between the speech data and at least one longer-term measurement of a speaker state analytic;
• and
• an output generation module configured to determine, based on the variable length time window, whether to output or hide particular speaker state data produced by one or more of the plurality of analytics engines.