Automated Transcription System for Malayalam Language

Dyuthi/Manakin Repository

Automated Transcription System for Malayalam Language

Show simple item record Kannan, Balakrishnan Cini, Kurian 2014-07-22T06:04:00Z 2014-07-22T06:04:00Z 2011-04
dc.description International Journal of Computer Applications (0975 – 8887) Volume 19– No.5, April 2011 en_US
dc.description.abstract 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. en_US
dc.description.sponsorship Cochin University of Science & Technology en_US
dc.language.iso en en_US
dc.subject HMM en_US
dc.subject MFCC en_US
dc.subject Speech Recognition en_US
dc.subject Transcription systems en_US
dc.title Automated Transcription System for Malayalam Language en_US
dc.type Article en_US

Files in this item

Files Size Format View Description
Automated Trans ... for Malayalam Language.pdf 202.8Kb PDF View/Open pdf

This item appears in the following Collection(s)

Show simple item record

Search Dyuthi

Advanced Search


My Account