Extracting User Preferences by GTM for aiGA Weight Tuning in Unit Selection Text-to-Speech Synthesis

• Published in: Computational and Ambient Intelligence Vol. 4507; pp. 654 - 661
• Main Authors: Formiga, Lluís, Alías, Francesc
• Format: Book Chapter
• Language: English
• Published: Germany Springer Berlin / Heidelberg 2007; Springer Berlin Heidelberg
• Series: Lecture Notes in Computer Science
• Subjects: Gaussian Mixture Model; Pareto Front; Speech Synthesis; User Preference; Weight Combination
• ISBN: 9783540730064; 3540730060
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-540-73007-1_79

Unit-selection based Text-to-Speech synthesis systems aim to obtain high quality synthetic speech by optimally selecting previously recorded units. To that effect these units are selected by a dynamic programming algorithm guided through a weighted cost function. Thus, in this context, weights should be tuned perceptually so as to be in agreement with perception from listening users. In previous works we have proposed to subjectively tune these weights through an interactive evolutionary process, also known as Active Interactive Genetic Algorithm (aiGA). The problem comes out when different users, although being consistent, evolve to different weight configurations. In this proof-of-principle work, Generative Topographic Mapping (GTM) is introduced as a method to extract knowledge from user specific preferences. The experiments show that GTM is able to capture user preferences, thus, avoiding selecting the best evolved weight configuration by means of a second preference test.