AUDIO SAMPLES – Paper at INTERSPEECH 2017
You can play some audio samples generated by the MagPhase Vocoder proposed in F. Espic, C. Valentini-Botinhao, and S. King, “Direct Modelling of Magnitude and Phase Spectra for Statistical Parametric Speech Synthesis,” in Proc. Interspeech, Stockholm, Sweden, August, 2017. [pdf, samples, and code]
AUDIO SAMPLES – Paper at INTERSPEECH 2016
You can play some audio samples of the method for waveform generation proposed in F. Espic, C. Valentini-Botinhao, Z. Wu, and S. King, “Waveform generation based on signal reshaping for statistical parametric speech synthesis,” in Proc. Interspeech, San Francisco, CA, USA, September, 2016. [pdf]
VOICE-SYNTH is a musical instrument programmed in C++ (RackAFX), based on the classical source-filter model of speech production. This video is a live demo that took place at the University of Miami, 2011.