International Journal of Engineering Research

Open Access Open Access  Restricted Access Subscription Access

Speech Analysis for Alphabets in Bangla Language:Automatic Speech Recognition


Affiliations
1 School of Computer Science and Software Engineering, University of Wollongong, Australia
 

This paper presents a technique for recognizing spoken letter in Bengali Language. We first derive feature from spoken letter. Mel-frequency cepstral coefficient (MFCC) has been used to characterize a feature. Dynamic time warping (DTW) employed to calculate the distance of an unknown letter with the stored ones. K-nearest neighbors (KNN) algorithm is used to improve accuracy in noisy environment.

Keywords

Automatic Speech Recognition (ASR), MFCC, DTW, KNN, Bengali Alphabets.
User
Notifications
Font Size

Abstract Views: 131

PDF Views: 0




  • Speech Analysis for Alphabets in Bangla Language:Automatic Speech Recognition

Abstract Views: 131  |  PDF Views: 0

Authors

Asm Sayem
School of Computer Science and Software Engineering, University of Wollongong, Australia

Abstract


This paper presents a technique for recognizing spoken letter in Bengali Language. We first derive feature from spoken letter. Mel-frequency cepstral coefficient (MFCC) has been used to characterize a feature. Dynamic time warping (DTW) employed to calculate the distance of an unknown letter with the stored ones. K-nearest neighbors (KNN) algorithm is used to improve accuracy in noisy environment.

Keywords


Automatic Speech Recognition (ASR), MFCC, DTW, KNN, Bengali Alphabets.