Speech synthesis refers to the automatic generation of speech from some symbolic representation. There are various interpretations of both the input and the output of speech synthesis. In the widest sense, the input may be a single (or multiple) switch(es) that can activate the generation of an announcement. In its simplest form, it can be a tape recorder or a similar device. Even this simple solution can be useful for people with both speech and hand motion positioning impairment.

In most modern cases, however, the input is text, and the output should be the corresponding speech. The precise definition in this case is text-to-speech synthesis (TTS). TTS systems are by definition language dependent. Multilingual systems can generate speech in multiple languages, but the voice of each ...

  • Loading...
locked icon

Sign in to access this content

Get a 30 day FREE TRIAL

  • Watch videos from a variety of sources bringing classroom topics to life
  • Read modern, diverse business cases
  • Explore hundreds of books and reference titles