New achievement of DeepO Band: Making Santour music by artificial intelligence using language modeling and deep learning
Mohammad Hasan Olyaei Torqabeh 1, *, Ali Olyaei Torqabeh 2 , Amir Hossein Sedghi 3
1. Faculty of Electrical Engineering, Sadjad University of Technology, Mashhad, Iran,
*این آدرس ایمیل توسط spambots حفاظت می شود. برای دیدن شما نیاز به جاوا اسکریپت دارید
2. Department of Computer Engineering, Faculty of Engineering, Ferdowsi University of Mashhad, Mashhad, Iran
این آدرس ایمیل توسط spambots حفاظت می شود. برای دیدن شما نیاز به جاوا اسکریپت دارید
3. Head of Music Committee of Islamic Art and Culture Center, Sadjad University of Technology, Mashhad, Iran
این آدرس ایمیل توسط spambots حفاظت می شود. برای دیدن شما نیاز به جاوا اسکریپت دارید
Today, the use of language modeling has been widely used, and this can be used in most issues that require learning rules and instructions. Some scholars have used this tool to model text and others to model audio and music, and then to make new texts and new music. This article discusses the modeling of Persian Santour music using long short-term memory (LSTM). To date, Santour has not been produced using artificial intelligence, and this is the first idea to be presented by the DeepO Band. This paper first discusses the LSTM network. To train the model, the number of 2000 notes from famous Santour music is selected. After the training phase, two Santour music was produced by this model, and the results indicate that the modeling process has been well done, and Artificial Intelligence has been able to make and play new music with the Santour instrument.
Keywords: Language Modeling, Artificial Intelligence, Santour, Music, DeepO Band, LSTM
