Fig. 1From: A unit selection text-to-speech-and-singing synthesis framework from neutral speech: proof of conceptUS-TTS&S framework. Block diagram of the unit-selection text-to-speech and singing (US-TTS&S) synthesis framework from neutral speech. In the speech mode, an input text is converted into synthetic speech by the TTS subsystem (above in the blue box). In the singing mode, the incorporation of the speech-to-singing (STS) subsystem (below in the red box) enables the framework to produce synthetic singing from an input score S (containing both the notes and the lyrics), considering optional input values: tempo T in beats per minute and transposition x in semitonesBack to article page