Hybrid HMM/ANN based isolated Hindi word recognition

Author

Kapse, Y. ; Londhe, N.D.

Author_Institution

Dept. of Electr. Eng., Nat. Inst. of Technol. Raipur, Raipur, India

fYear

2014

fDate

11-13 Dec. 2014

Firstpage

1

Lastpage

5

Abstract

Automatic speech recognition has become one of the most challenging task in the field of pattern recognition and natural language processing. In this paper, a hybrid model is proposed for isolated Hindi word recognition. This hybrid model involves the iterative training procedure. HMM is employed to induce the state transition probability distribution and ANN is employed as a classifier. HMM is designed by 4-state left to right model. In the proposed model ten Hindi words are used for the samples and five speakers for training and five distinct speakers for testing purpose and therefore the performance has achieved upto 89.8%.

Keywords

hidden Markov models; natural language processing; neural nets; signal classification; speech recognition; statistical distributions; Hidden; artificial neural network; automatic speech recognition; classifier; hidden Markov model; hybrid HMM-ANN based isolated Hindi word recognition; iterative training procedure; natural language processing; pattern recognition; state transition probability distribution; Artificial neural networks; Automatic speech recognition; Hidden Markov models; Speech; Text recognition; Artificial Neural Network (ANN); Hidden Markov Model (HMM); Speech recognition; iterative training procedure; state transition probability distribution;

fLanguage

English

Publisher

ieee

Conference_Titel

India Conference (INDICON), 2014 Annual IEEE

Conference_Location

Pune

Print_ISBN

978-1-4799-5362-2

Type

conf

DOI

10.1109/INDICON.2014.7030373

Filename

7030373