Speech Synthesis

From Wikiversity
Jump to navigation Jump to search

In this learning resource we distinguish between Speech Synthesis for a text and the audio synthesis in general that incorporates more the creating an audio output for standard text e.g. in English.

Learning Task[edit | edit source]

  • Explain the benefit of Speech Synthesis for blind people. What are the requirements and constraints for web portal, so that for Speech Synthesis can be used for blind people and identify barriers e.g. if information is encoded in images, which can be used for text input for Speech Synthesis.
  • Explain how Speech Synthesis and Speech Recognition in conjunction be used to reduced the required bandwidth for an audio transmission.
  • A MIDI sequence defines which note was pressed, how long it was pressed and how hard you hit the key on a MIDI keyboard. Explain the similarities and difference between Speech Synthesis and Audio Synthesis from MIDI file with a General MIDI Soundfont (see Online Music Jam).
  • Compare Speech Synthesis for the text input with an audio synthesis for a sequence of phonems, what are the benefits and drawbacks for the application in the context of Audio-Video-Compression.

See also[edit | edit source]