Monophone and Triphone Acoustic Phonetic Model for Kannada Speech Recognition System

Simple item page
dc.contributor.authorKumar, T.N.M.
dc.contributor.authorJayan, A.
dc.contributor.authorBhat, S.
dc.contributor.authorAnvith, M.
dc.contributor.authorNarasimhadhan, A.V.
dc.date.accessioned2026-02-06T06:35:38Z
dc.date.issued2022
dc.description.abstractThe automatic Speech Recognition system (ASR) is the most widely used application in the speech domain. ASR systems generate text data from spoken utterances without manual intervention. In this work, we build an ASR system for the Kannada language. For building the proposed system, we extract Mel Frequency Cepstral Coefficients (MFCC) features from the audio data, and the Kannada language model is developed using corresponding labels. The dictionary generation and phonetic labelings are automated. Recognition performance is compared for both monophonic and triphone models. The word error rate of 15.73 % and the sentence error rate of 55.5 % are achieved for the triphone model. Comparatively, the triphone model gives a better performance than the monophonic model. © 2022 IEEE.
dc.identifier.citation2022 International Conference on Wireless Communications, Signal Processing and Networking, WiSPNET 2022, 2022, Vol., , p. 336-340
dc.identifier.urihttps://doi.org/10.1109/WiSPNET54241.2022.9767115
dc.identifier.urihttps://idr.nitk.ac.in/handle/123456789/29979
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.subjectAutomatic Speech Recognition
dc.subjectHMM
dc.subjectKannada language
dc.subjectMFCC
dc.titleMonophone and Triphone Acoustic Phonetic Model for Kannada Speech Recognition System

Files

Collections

Conference Papers