Study of Speech Recognition Using CNN

Ramesh Babu Pittala, B.R Tejopriya, Esha Pala

20222022 Second International Conference on Artificial Intelligence and Smart Energy (ICAIS)30 citationsDOI

Abstract

Artificial Neural Networks is one of the most preferable topics in Machine Learning. Various applications like Google Assistant, Google Translator, Apple Siri, etc are implemented on these Artificial Neural Networks. All these applications are based on Speech Recognition. Nowadays Speech Recognition plays a prominent role in many fields, the machine can recognize words and sentences in spoken language and translate them into machine-readable formats. Different methods of speech recognition include Hidden Markov Model (HMM), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), etc. The main objective of this paper is to know how MFCC is helpful in the recognition of speech commands spoken by the speakers using Convolutional Neural Networks. Convolutional neural networks help train the machine to recognize the spoken words by using Speech Recognition.

Topics & Concepts

Computer scienceHidden Markov modelConvolutional neural networkSpeech recognitionRecurrent neural networkArtificial intelligenceArtificial neural networkTime delay neural networkMel-frequency cepstrumSpeaker recognitionFeature extractionNatural language processingSpeech Recognition and SynthesisSpeech and Audio ProcessingMusic and Audio Processing