Extraction of Linguistic Information with the AID of Acoustic Data to Build Speech Systems

Linguistic knowledge plays a major role in building high quality speech systems such as speech synthesizer and speech recognizer systems. Quality of such speech systems greatly depends on the availability of linguistic knowledge such as pronunciation dictionary, stress pattern, syllable structure and so on. However, it is very difficult to obtain these linguistic knowledge in the required format for most of the languages. In this paper an attempt has been made to design and develop tools for extraction of the core linguistic information (letter to sound rule) automatically with the aid of acoustic data to build improved quality speech systems. Acoustic evidences will be exploited with minimal language knowledge to deploy the vital linguistic resources for such systems. The resulting letter to sound (LTS) rule is tested on different test data on Amharic, Hindi and Tamil. The performance of the letter-to-sound rule is reported in this paper.