Speech Processing
by Computer
LECTURE 8
SIGNAL GENERATION FOR SPEECH SYNTHESIS
Objectives
By the end of the
session you should be able to:
·
describe the basic operation of concatenative signal generation systems
·
describe in general terms the signal processing requirements of
concatenative systems
·
describe the basic operation of formant synthesis systems
·
discuss the relative advantages and disadvantages of concatenative and
formant techniques for signal generation.
Outline
8. Signal Generation
8.1. Requirements
8.2. Concatenative
Synthesis
8.2.1. Diphones
8.2.2. Other units
8.2.3. Corpus based
8.2.4. Signal Processing
8.2.4.1.Duration
modification
8.2.4.2.Pitch
modification
8.2.4.3.Smoothing at
joins
8.3. Formant Synthesis
8.3.1. Architecture
8.3.1.1.Series vs.
parallel
8.3.2. Parameter
generation
8.4. Articulatory
Synthesis
8.4.1. Aims &
problems
8.4.2. High-level
synthesis
Readings
General:
T.
Dutoit, “Synthesis Strategies”, in An introduction to text-to-speech
synthesis, Kluwer 1997.
Specific:
P.
Bhaskararo, "Subphonemic segment inventories for concatenative speech
synthesis", in Fundamentals of Speech Synthesis and Speech Recognition,
ed Eric Keller, Wiley, 1994.
C. Hamon, E. Moulines, F. Charpentier, "A Diphone Synthesis System based on Time-Domain Prosodic Modifications of Speech", Proc. Int. Conf. Acoustics Speech and Signal Processing, 1989, pp238-241.
D. Klatt, “Software for a cascade/parallel formant synthesizer”, J.Acoust.Soc.Am 67(3) 1980, 971.