Мистюков Евгений Владимирович
Music Composition Adaptation to Certain Music Style Based on Machine Learning Algorithms
Системная и программная инженерия
Machine learning sphere is one of the most important and growing science sphere nowadays. Many algorithms dealing with images exist, but attention to music is growing as well. Some algorithms classify music by genre while others developed recently deal with music generation. The idea of this work is to develop an algorithm, which given two songs as an inputs will mix them to provide an audio output. This work provides theoretical basis of neural networks and convolutional neural networks in particular, describes how to construct a working model to create an audio output from two inputs, and shows how the network parameters can be evaluated and changed to fit the model better and generate better results.
Текст работы (работа добавлена 5 июня 2017г.)