Challenges of Accent and vowels for Sindhi Speech Recognition System

While talking and writing in Sindhi language, many challenges are faced because of the large number of 52 characters or alphabets. Vowels and the accent keep changing in fluency of speaking and writing. Due to the different varities of languages in the world and the dearth of computer scientists in the field of Speech Recognition, it is considered difficult area of study and is the least advanced field of Artificial Intelligence. More specifically, the difficulties are faced in the speech recognition for languages like Arabic and its adapting languages such as Sindhi, Pashto, Urdu, and others. The script and sounds in every language are directly proportional to each other i.e. the shorter script has less sounds while the longer script has more sounds. We developed a system for speech to text recognition system for Sindhi language with the help of Sphinx model. We have also tested the different datasets through the input in various phases and compare the results and accuracy of the vowels and accents through the proposed system