Text-to-Speech

Introduction

1. What was von Kempelen’s speaking machine?
   The first full-sentence speech synthesizer (1769–1790): bellows for lungs, a reed for vocal folds, a rubber mouthpiece and nose aperture, whistles for fricatives and a small bellows for plosive puffs, played with levers by an operator. (Unlike his chess-playing Mechanical Turk, it was not a hoax.)
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 17, Introduction, p. 383
2. What is text-to-speech (TTS)?
   Speech synthesis: mapping text to an acoustic waveform, the reverse of ASR.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 17, Introduction, p. 383
3. Name applications of TTS.
   Spoken language models that interact with people, reading text aloud, games, and producing speech for people who have lost their voice to neurological disorders (e.g. ALS).
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 17, Introduction, p. 383