A Literature Survey on Recurrent Neural Network and Various Techniques for Speech Recognition

Speech is the vocalized form of human communication. Each spoken word is created out of the phonetic combination of a limited set of vowel and consonant speech sound units. Speech Recognition (SR) is the ability of a machine or program to identify words and phrases in spoken language and convert them to a machine-readable format. SR has evolved quite a bit over the past few years and the Initially it used to work in discrete dictation mode where you had to pause and stop between every spoken word. Today, however it uses continuous dictation, It is also become smarter with its own set of grammar rules to make out the meaning of what is being said. In this work, different method is used for Speech Recognition (SR) in Recurrent Neural Network (RNN) which improve the performance SR.