Speech recognition using deep neural network - recent trends
International Journal of Intelligent Systems Design and Computing
Deep neural networks (DNN) are special forms of learning-based structures composed of multiple hidden layers formed by artificial neurons. These are different to the conventional artificial neural networks (ANN) and are accepted as efficient tools for solving emerging real world problems. Recently, DNNs have become a mainstream speech recognition tool and are fast becoming part of evolving technologies emerging as a viable option to replace all other leading tools so far used. ANNs with deep
... rning which uses a generative, layer by-layer pre-training method for initialising the weights has provided best solution for acoustic modelling for speech recognition. This paper provides a brief description of the current technology related to speech recognition and its slow adoption of DNN-based approaches. Initially, a historical note on the technology development for speech recognition system is given. The later part explains the DNN-based acoustic modelling for speech recognition and recent technology developments reported and the ones available for actual use. Reference to this paper should be made as follows: Sarma, M. (2017) 'Speech recognition using deep neural network -recent trends', Int. . She completed her MSc in Electronics and Communication Technology from Gauhati University, India in 2010. She also completed her MTech from the same institution in 2012 with specialisation in Speech Processing and Recognition. She is currently pursuing her PhD in the area of application of softcomputing tools in the area of speech recognition. She has co-authored two books and published several peer reviewed research papers in international conference proceedings and journals. She serves as a reviewer to several journals and IEEE international and national conferences. Her areas of interest include speech recognition, soft-computation and HCI applications.