Unit selection speech synthesis creates speech by re-sequencing pre-recorded speech units selected from a speech database. The selection of the best unit sequence from the database is treated as a search problem in this book. The unit selection process is based on minimization of target cost and joins cost.This book introduces Simulated Annealing (SA) algorithm to solve unit selection problem in speech synthesis.Viterbi algorithm is commonly used to solve unit selection problem.However,viterbi algorithm consume large amount of computation when speech database is large.The advantage of using SA over viterbi algorithm is shorter computational time is needed since SA not consider the entire hypothesis in the database.Implementation of SA algorithm in this book provide audience about the concept of SA and how it can be implemented in unit selection.