Main Article Content

Abstract

Audio analysis is fast becoming a requirement of digital media for analysing multiple frequencies of sound at a time and also reduce the background noise.The urban sound challenge  is increasing day by day and the problem is meant to introduce  for audio analysis and processing in the usual classification scenario. Model is implemented on the basis of keras framework and librosalibrary. Keras is capable of running of the algorithm tensorflow. Kerascan be described as an interface rather than a standalone machine learning tools. Librosa is one of the python library for music and audio analysis. It helps us with necessary music information retrieval systems.


The authorcollect the database and use the data and also use the graph for a better understanding of audio data analysis.

Keywords

os pandas librosa keras glob numpy sklearn

Article Details

Citations
GHOSH, S. (2020). IMPLEMENTATION OF MACHINE LEARNING AND DEEP LEARNING IN IMPROVING SIGNAL TO NOISE RATIO FOR AUDIO ANALYSIS IN DIGITAL MEDIA PLATFORMS. [email protected] - Preprint Archive, 1(1). https://doi.org/10.36375/prepare_u.a65

References

  1. Gideon mendels,”how to apply deep learning and machine learning method in audio analysis”, Nov,2019
  2. Acton, Ciaran,” analysis of variance(ANOVA)”,2009
  3. Mitchell,”machine learning”,1997
  4. Bishop,C.M,”pattern recognition and machine learning”,2006
  5. Schmidhuber, “deep learning in neural network”,2015
  6. FaizanShaikh,”getting started with audio data analysis using deep learning”, August,2017
  7. G.W.Smith,” The machine as Artist”,April,2017
  8. Shen,yelong,”a latent semantic model with convolution-pooling structure for information retrieval”,October,2013
  9. Jotikasingh,”introduction to audio processing”,September,2019
  10. A.Huang, and R.Wu,”deep learning for music”
  11. N.Jaitly and G.Hinton,”learning a better representation og speech soundwaves using neural networks”,2011