I’m a Ph.D. student of computer science with over seven years of industrial experience in information technology and over four years of experience in Artificial intelligence, Data science, and machine learning. I have led multiple AI projects associated with time series and large-scale data and participated in multidisciplinary national projects. I’m passionate about new technologies and challenges, which cause growth and learning opportunities, especially in interdisciplinary projects, leading to the collaboration and teamwork of diverse experts from different backgrounds. 

Besides my work, my studies generally lie in the intersection of Music (Also NLP for poems and lyrics) and Computer Science and its collaboration with various fields related to mental health (especially kids). I create Deep learning models for Music, Audio, and Speech processing mostly to connect none musicians to Music with a better perspective. I found out that Music and poetry have a significant impact on kids, and I like to expand my research to study the psychological aspects of Music and poetry on kids using Artificial intelligence. Therefore, I'm interested in connecting Deep learning and AI with Psychology, Neuroscience, and Medical (images) in general or specifically related to Music.

Personal Life

I think it’s obvious that I’m crazy about music! I like to sing and play guitar, especially with my daughter (mostly Iranian traditional singing). Moreover, I have the honor of being in the choir of the Mehrzad Khajeamiri concert Group. I write poems and lyrics, some of which are available here, and you can watch my singing videos on my YouTube channel. Furthermore, I enjoy designing logos and websites, which can be found here. Finally, Games, audiobooks, and podcasts are inseparable parts of my life! 

Thesis Title: "Persian modal music (Dastgah) Detection using Deep Neural Networks "

Abstract:

In this research, several deep neural networks are implemented to recognize Persian modal music in  seven high correlated categories. The best model which achieved 92 percent overall accuracy is using an architecture inspired by Autoencoder including BiLSTM and BiGRU layers. This model is trained by using Nava dataset which has 1786 records and up to 50 hours of worth of music played solo by Kamanche, Tar, Setar, Ney, and Santoor(Dulcimer). Features that have been studied through this research, contain MFCC, Chroma feature and Mel spectrogram. The results indicate that MFCC carries more valuable information about Persian modal music than other features. Moreover, The architecture which is inspired by autoencoders is powerful in distinguishing high correlated data like Persian modal music. It also shows that because of the precise order in Iranian Dastgah Music, Bidirectional Recurrent networks are more efficient than any other network that has been implemented in this research. (Github  link)