Ways to generate computer speech

1
Ways to generate computer speech

• Record a human speaking every sentence HAL will
  ever speak (not likely)
• Make a mathematical model of the human vocal
  tract (synthesis)
• Record a human speaking a lot of sentences, and
  come up with some way of making new sentences out
  of the recorded ones (concatenation)

2
What goes into synthesizing speech?

• Have some idea of what human speech actually
  looks/sounds like
• Modeling the shape of a speakers mouth
• Fricative noises and noises from stops
• Pitch changes
• Produce sounds that resemble speech sounds

3
Synthesis Putting it all together

• Shape of mouth 1 2 3
• all 3
• Fricative and burst noises
• Shape of mouth and fricative noises
• Shape of mouth, fricative noises, pitch

4
Speech synthesis

• (1980) The Speak Spell toy used a synthesis
  process called Linear Predictive Coding (LPC).
• Basically, LPC is a way for a computer to extract
  all of the different parts of speech from a
  speech signal, and re-create them using a
  mathematical model of the vocal tract
• Heres a better example of LPC (1982)
• LPC is used today for GSM phone systems

5
Text-to-Speech (TTS) systems

• Concatenative synthesis
• Record natural speech
• Chop speech up into units
• Recombine units according to the phonetic
  transcription to be pronounced
• Steps for a TTS system
• Start w/ written text
• Convert text to phonetic characters
• Find segments of speech in database
• Calculate intonation of sentence

6
Text-to-Speech (TTS) systems

• Examples of text from The North Wind and the Sun
  (Aesop), circa 2005
• Mike (ATT)
• Crystal (ATT)
• British English (Rhetorical Systems)
• Scottish English (Rhetorical Systems)