Abstract
The performance of an Automatic Speech Recognition (ASR) system can be improved by using knowledge about the phonetic structure of a language. This paper discusses an Automatic Language Recognition (ALR) algorithm which can recognize the language of the input speech so that the knowledge component specific to that language can be activated in an ASR designed for more than one language. Performance of the ALR algorithm developed for three languages—Hindi, English and Telugu, is also discussed.
Full Text
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call