Urdu speech recognition system for district names of Pakistan: Development, challenges and solutions

Speech interfaces provide people an easy and comfortable means to interact with computer systems. Speech recognition is a core component of speech interfaces which recognizes human speech in a particular language. Some small vocabulary speech recognition systems for Urdu language with reasonable accuracy have been developed but these systems are either speaker dependent or unable to handle the large accent variations that exists among people of Pakistan. This paper presents a speaker independent Urdu speech recognition system for district names of Pakistan that performs well for major accents of Urdu. Two methods have been studied and analyzed to handle accent variation. The systems have been tested in laboratory and field and their results have been reported in this paper. We conclude that accent independent system performs better for isolated words and addition of field data in the training of system improves the overall recognition accuracy.