Automated Transcription System for Malayalam Language
Cini Kurian, Kannan Balakrishnan · International Journal of Computer Applications · 2011
Malayalam is one of the 22 scheduled languages in India with more than 130 million speakers.This paper presents a report on the development of a speaker independent, continuous transcription system for Malayalam.The system employs Hidden Markov Model (HMM) for acoustic modeling and Mel Frequency Cepstral Coefficient (MFCC) for feature extraction.It is trained with 21 male and female speakers in the age group ranging from 20 to 40 years.The system obtained a word recognition accuracy of 87.4% and a sentence recognition accuracy of 84%, when tested with a set of continuous speech data.