Abstract: Described is a voice generation system. The voice generation system comprises a housing comprising a first opening and a second opening. The housing defines an air passage between the first opening and the second opening. The voice generation system comprises a moveable member located within the housing. The moveable member is configured to vibrate in response to air flowing in the air passage. The voice generation system comprises a transducer module configured to convert vibrations of the moveable member into an electrical signal. The voice generation system comprises a speaker module configured to convert the electrical signal into sound and to output sound into the oral cavity of a user. The voice generation system is configured such that during use, the air pressure at or near the second opening corresponds to an air pressure in the oral cavity of the user.

Abstract: A system for reconstructing speech from an input signal comprising whispers is disclosed. The system comprises an analysis unit configured to analyse the input signal to form a representation of the input signal; an enhancement unit configured to modify the representation of the input signal to adjust a spectrum of the input signal, wherein the adjusting of the spectrum of the input signal comprises modifying a bandwidth of at least one formant in the spectrum to achieve a predetermined spectral energy distribution and amplitude for the at least one formant; and a synthesis unit configured to reconstruct speech from the modified representation of the input signal.