Systems and methods are disclosed for synthesizing speech from minute facial skin movements. In one implementation, a system may include a processor configured to control at least one coherent light source to illuminate a region of a face. The processor may receive from at least one sensor, reflection signals indicative of coherent light reflected from the face. The reflection signals may be analyzed to determine the minute facial skin movements associated with silent speech. Then, based on the determined minute facial skin movements, the processor may determine a sequence of words associated with the silent speech, and synthesize the sequence of words associated with the silent speech into audio signals.