This paper aims at designing and implementation of Hindi number recognition system using the microphone and mobile recorded speech. Spectral features known to represent phonetic information are used as the features to characterize different Hindi digits. Gaussian mixture models (GMM) are used to develop the digit recognition system. This paper focuses on the ten basic Hindi digits where '0' is pronounced as 'shunya' to '9' is pronounced as 'no'. Data has been collected separately from male, female and child speakers using microphone and mobile phone device. The experimental results show that the overall accuracy of digit recognition is 98.9\% in the case of microphone recorded speech and 96.4\% in the case of mobile phone recorded speech. Keywords-Gaussian mixture models (GMM), Mel frequency cepstral coefficients (MFCC), Hindi digit microphone database (HDMD), Hindi digit telephonic database (HDTD).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.