|
Dyuthi @ CUSAT >
e-SCHOLARSHIP >
Computer Applications >
Faculty >
Dr. Kannan Balakrishnan >
Please use this identifier to cite or link to this item:
http://purl.org/purl/4190
|
| Title: | Speech Recognition of Malayalam Numbers |
| Authors: | Kannan, Balakrishnan
Cini, Kurian |
| Keywords: | Digit speech recognition
automatic data entry
PIN entry
Mel frequency cepstrum coefficient (MFCC)
Hidden Markov model (HMM) |
| Issue Date: | 9-Dec-2009 |
| Publisher: | IEEE |
| Abstract: | Digit speech recognition is important in many
applications such as automatic data entry, PIN entry, voice
dialing telephone, automated banking system, etc. This
paper presents speaker independent speech recognition
system for Malayalam digits. The system employs Mel
frequency cepstrum coefficient (MFCC) as feature for
signal processing and Hidden Markov model (HMM) for
recognition. The system is trained with 21 male and female
voices in the age group of 20 to 40 years and there was
98.5% word recognition accuracy (94.8% sentence
recognition accuracy) on a test set of continuous digit
recognition task. |
| Description: | Nature & Biologically Inspired Computing, 2009. NaBIC 2009. World Congress on |
| URI: | http://dyuthi.cusat.ac.in/purl/4190 |
| Appears in Collections: | Dr. Kannan Balakrishnan
|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
|
