Open AccessAudio Event Identification and Classification for Cricket Sports using LSTM
Author(s) -
Pankaj Kumar,
John Sahaya Rani Alex
Publication year - 2019
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.d9462.118419
Subject(s) - mel frequency cepstrum , computer science , event (particle physics) , cricket , speech recognition , artificial neural network , context (archaeology) , identification (biology) , artificial intelligence , audio signal , sound recording and reproduction , pattern recognition (psychology) , machine learning , feature extraction , speech coding , ecology , paleontology , physics , botany , quantum mechanics , acoustics , biology
Audio event identification is an emerging research topic to augment the automation of audio tagging, context-based audio event retrieval, audio surveillance and much more. In this research work, audio event classification for cricket commentary is done by using long short term memory (LSTM) neural network. Mel-frequency cepstral coefficients (MFCC) features are extracted from the audio commentary and trained with LSTM neural network. The trained LSTM network is validated and attained an accuracy of 95%.