ICADS '22 Talk: Deep Learning for Melodic Frameworks

57 views

IEEE Computer Society

Create Account or Sign In to post comments

#Machine Learning #Artificial Intelligence #Generative Adversarial Network #GAN #CycleGAN #Indian Classical Music #scv-cs #Melodic Frameworks #Deep Learning

Audio signals that appeal to the ear and create melody usually confirm a structural framework. This video presentation gives insights into our deep learning experiments on audio signals, particularly with respect to latent melodic frameworks within them.

Audio is one of the four data types that deep learning works best on, the other three being image, video, and text. The talk discusses applying Deep Learning to audio signals, how Fourier Transform, Ordinary Differential Equations, and Legendre Polynomials are used in the context of Deep Learning and presents some emerging trends that are worth watching in this space.

Speaker Dr. Vishnu S. Pendyala, presented this talk virtually, at SJSU (San José State University) during the IEEE Computer Society, Santa Clara Valley Chapter’s International Conference on Applied Data Science (ICADS'22) on July 12, 2022.

For access to past video webinars or to join our Dlist to hear about future programs, please visit https://r6.ieee.org/scv-cs

Audio is one of the four data types that deep learning works best on, the other three being...