Title: SOCS: A Speech Output System from Concept Representation
Author: Yoichi Yamashita and Riichiro Mizoguchi
Reference: Proc. of 1992 International Conference on Acoustics, Speech, and Signal Processing (ICASSP '92), San Francisco, Vol.2, pp.69-72.
This paper describes a Concept-To-Speech (CTS) conversion system, SOCS (Speech Output from Case Structure representation). For CTS systems, how to represent the input to the system is a very important issue to discuss. In SOCS, a representation based on case structure and phrase patterns, which is called concept representation, is converted into synthetic speech. SOCS plays a crucial role in a speech output interface which is designed as a general frontend of various intelligent performance systems (IPS). The message transmission of the concept representation satisfies the requirements both from IPS and the speech synthesis component. SOCS has two new built-in mechanisms for direct control of prosodic parameters by a concept representation. The first one is the pause marker which is generated along with words in the sentence generation. The pause marker is used both to insert pauses and to set the boundaries of the prosodic phrase component of f0. The second one is the Prosody Modification Functions (PMF) embedded in the custom templates. PMF controls the the prosodic parameters for the prepared sentence pattern. The dialog management in a speech output interface based on SOCS is also discussed.
Ftp article (ps-file, 4 pages, 192868 bytes)