Hmm-dnn speech recognition techniques: a review
International Journal of Development Research
Hmm-dnn speech recognition techniques: a review
Received 27th April, 2017; Received in revised form 19th May, 2017; Accepted 26th June, 2017; Published online 31st July, 2017
Copyright ©2017, Pallavi Saikia. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
This paper presents a view about the HMM-DNN hybrid approach for speech recognition. Speech recognition is becoming an active research area in the field of computer science. Many researchers have developed a good deal of methods and techniques for speech recognition. A new trend is to use hybrid approaches for this particular task. One of this hybrid approaches is to use a combination of HMM-DNN and the result is found to be quiet successful. From study it has been found that the above approach outperforms the other traditional methods like GMM-HMM. This paper gives a basic idea about HMM and DNN model and then finally the use of HMM-DNN hybrid approach in different speech recognition techniques.
