|Type of Publication:||Article|
|Authors:||A. S. Madhukumar, S. Rajendran, B. Yegnanarayana|
|Journal:||Computer Speech & Language||Volume:||7|
|Number:||3||Pages:||283 - 301|
In this paper, we describe some features of the fundamental frequency (F0) contours of speech in Hindi and propose an approach to represent and activate this intonation knowledge for an unrestricted text-to-speech system for Hindi. As in most languages, the declarative sentences in Hindi show a declining pattern of F0 contour, whereas interrogative sentences show a rising F0 contour. The backdrop declining or rising pattern is characterized by local falls and rises which are determined by the phonological pattern of the constituent words. In complex declarative sentences the F0 contour resets at major syntactic boundaries. Experiments to obtain the inherent F0 of segments are described. The intonation knowledge derived from analysis of speech is coded in a production system format. Intelligibility and naturalness of the synthesized speech improved significantly after incorporation of the intonation rules.