Triphone Model Based Novel Kannada Continuous Speech Recognition System using Kaldi Tool
Anand H.Unnibhavi1, D.S.Jangamshetti2, Shridhar K3
1Anand H. Unnibhavi, Dept. of Electronics and Communication Engineering Basaveshwara Engineering College Bagalkot, India.
2D.S. Jangamshetti, Dept. of Electrical and Electronics Engineering Basaveshwara Engineering College, Bagalkot, India.
3Shridhar K, Dept. of Electronics and Communication Engineering Basaveshwara Engineering College Bagalkot, India.
Manuscript received on June 18, 2020. | Revised Manuscript received on June 26, 2020. | Manuscript published on July 10, 2020. | PP: 452-458 | Volume-9 Issue-9, July 2020 | Retrieval Number: 100.1/ijitee.I7210079920 | DOI: 10.35940/ijitee.I7210.079920
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Accent is one of the issue for speech recognition systems. Automatic Speech Recognition systems must yield high performance for different dialects. In this work, Neutral Kannada Automatic Speech Recognition is implemented using Kaldi software for monophone modelling and triphone modeling. The acoustic models are constructed using the techniques such as monophone, triphone1, triphone2, triphone3. In triphone modeling, grouping of interphones is performed. Feature extraction is performed by Mel Frequency Cepstral Coefficients. The system performance is analysed by measuring Word Error Rate using different acoustic models. To know the robustness and performance of the Neutral Kannada Automatic Speech Recognition system for different dialects in Kannada, the system is tested for North Kannada accent. Better sentence accuracy is obtained for Neutral Kannada Automatic Speech Recognition system and is about 90%. The performance is degraded, when tested for North Kannada accent and the accuracy obtained is around 77%. The performance is degraded due to the increasing mismatch between the training and testing data set, as the Neutral Kannada Automatic Speech Recognition system is trained only for neutral Kannada acoustic model and doesn’t include north Kannada acoustic model. Interactive Kannada voice response system is implemented to identify continuous Kannada speech sentences.
Keywords: ASR, NKASR, Linear Discriminant Ananlysis, Maximum Likelyhood Linear Transform, Speaker Adaptive Training.
Scope of the Article: Automatic Speech Recognition