Upadhyaya, P and Mittal, SK and Farooq, O and Varshney, YV and Abidi, MR (2019) Continuous hindi speech recognition using Kaldi ASR based on deep neural network. In: International conference on Machine Intelligence and Signal Processing, MISP 2017, 22 - 24 December 2017, Indore, pp. 303-311.
PDF
MISP_2017.pdf - Published Version Restricted to Registered users only Download (333kB) | Request a copy |
Abstract
Today, deep learning is one of the most reliable and technically equipped approaches for developing more accurate speech recognition model and natural language processing (NLP). In this paper, we propose Context-Dependent Deep Neural-network HMMs (CD-DNN-HMM) for large vocabulary Hindi speech using Kaldi automatic speech recognition toolkit. Experiments on AMUAV database demonstrate that CD-DNN-HMMs outperform the conventional CD-GMM-HMMs model and provide the improvement in word error rate of 3.1 over conventional triphone model.
Item Type: | Conference Paper |
---|---|
Publication: | Advances in Intelligent Systems and Computing |
Additional Information: | The copyright for this article belongs to Springer Verlag. |
Keywords: | Artificial intelligence; Deep neural networks; Hidden Markov models; Natural language processing systems; Signal processing; Speech, Automatic speech recognition; Context dependent; Hindi language; Kaldi; Large vocabulary; Triphones; Word error rate, Speech recognition |
Department/Centre: | Division of Electrical Sciences > Electrical Communication Engineering |
Date Deposited: | 15 Nov 2022 09:38 |
Last Modified: | 15 Nov 2022 09:38 |
URI: | https://eprints.iisc.ac.in/id/eprint/78047 |
Actions (login required)
View Item |