Collection and Analyses of Exemplary Speech Data to Establish Easy-to-Understand Speech Synthesis for Japanese Elderly Adults

Abstract

This paper describes a newly developed Japanese speech database in order to find the features of speech and speaking styles that elderly adults actually think is easy to understand for establishing speech synthesis for elderly adults. This speech database is characterized by two features: i) its sentences are largely taken from newsletters beyond just the contents that elderly adults tend to know; ii) the sentences are spoken by exemplary speakers selected through an audition process from the perspective that elderly adults actually think is easy to understand. This paper describes the design of our database and the basic characteristics measured by applying conventional theories. Finally it indicates the extension directions of the conventional theories to establish an easy-to-understand speech synthesis method for elderly adults.