In this paper authors describes the automatic music generation system and automatic music evaluation system. The system composes short pieces of music by choosing some factors in music, such as timbre, pitch interval, rhythm, tempo etc. The most important features of the system the music is generated according to the mood and sentiments of person. In the implemented work mode control the pitch interval and density control the rhythm of music. Neural Network Algorithm for automatic evaluation system of music. Music composition is an art, even the task of playing composed music takes considerable effort by humans. Given this level of complexity and abstractness, designing an algorithm to perform both the tasks at once is not obvious and would be a fruitless effort. In this paper authors describe new music composition by using trained music data set to extract useful music pattern and generate the music in the form of chord.In this paper also discussed about method or platform use for automatic music generation.

Music Generator, Generative Model, The Restricted Boltzman Machine, MIDI file, Tensorflow

[1] Akshay Jakhotiya, Ketan Kulkarni, Chinmay Inamdar, Bhushan Mahajan, Alka Londhe "Automatic Subtitle Generation for English Language Videos",2018,PP No.2-6
[2] Shubham Jain; A. Pandian; “survey on automatic music generation", 2018, PP NO.2-3
[3] Briot,J.;Hadjeres, G.; and Pachet, F. 2018.DeepLearning Techniques for Music Generation Springer International Publishing.
[4] Chu, H.; Urtasun, R.; and Fidler, S. 2017. Song from PI: A musically plausible network for pop song generation. In Proc.International Conference on Learning Representations (ICLR), Workshop Track.
[5] Blaauw, M., and Bonada, J. 2017. A neural paramet
singing synthesizer. In Proc. Interspeech.
[6] Lin, J.-C., Wei, W.-L., and Wang, H.-M. DEMVmatchmaker: emotional temporal course representation and deep similarity matching for automatic music video generation. In ICASSP, 2016.
[7] Eric Malmi, Pyry Takala, Hannu Toivonen, Tapani Raiko, and Aristides Gionis. DopeLearning: A Computational Approach to Rap Lyrics Generation, arXiv :1505.04771v1 [cs.LG], 18 May 2015.
[8] Peter Potash, Alexey Romanov, Anna Rumshisky. GhostWriter: Using an LSTM for Automatic Rap Lyric Generation, proceedings of conference on Empirical Methods in NLP, 2015
[9] Margareta Ackerman and David Loker. Algorithmic Song writing with ALYSIA, arXiv:1612.01058v1 [cs.AI], 4 Dec 2016.
[10] Jukka M. Toivanen and Hannu Toivonen and Alessandro Valitutti. Automatical Composition of Lyrical Songs, in The Fourth International Conference on Computational Creativity, 2013.
[11] Automatic generation of song lyrics on a semantic domain. Journal of Artificial General Intelligence, 6(1):87–110, 2015.
[12] Dekai Wu and Karteek Addanki, Learning to Rap Battle with Bilingual Recursive Neural Networks, proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI 2015)
[13] PhilippeHamel,SimonLemieux,YoshuaBengioandDouglasEck,”Temporal Pooling and multiscale learning for automatic annotation and ranking of Music audio”,2015,PP.No.2-4.