A Knowledge-Based Design Environment for Speech Recognition Systems

Abstract

The progress in speech technology over the last 30 years has come to a stage, where simple yet practical speech recognition systems could be built. Designing of such systems is an evolutionary process requiring a lot of experimentation. This lengthy and involved process is a major hurdle in developing useful commercial systems like a voice-input telephone dialer. To overcome this problem, we propose the use of a knowledge-based design environment.

For analysing a given problem, a framework based on PR and AI concepts is explained using the example of a telephone dialer. Then some representative speech recognition/understanding systems are reviewed to give some idea about the design aspects like the system architecture, PR subtasks involved, AI techniques used etc. Finally the concept of a design environment is explained. The environment is considered as a collection of knowledge-based tools with a global knowledge-base about speech technology.

Indexing terms:

• Speech recognition systems
• voice-input telephone dialer