Music Generation for Novices Using Recurrent Neural Network (RNN)

Sajad, Sahreen; Dharshika, S; Meleet, Merin

doi:10.1109/icses52305.2021.9633906

Cited by 10 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Authors in [13] proposed an RNN-LSTM-based architecture to generate music; however, the shortcomings of this method are that the data is represented in ABC notation, which is a text based musical notation that lacks audio data and cannot be played directly without conversion to another format. It has limited expressive capabilities as it cannot represent change in tempo, dynamics, or articulation.…”

Section: Research Statusmentioning

confidence: 99%

Multi-Genre Symbolic Music Generation using Deep Convolutional Generative Adversarial Network

Chauhan,

Tanawala,

Hasan

2023

ITM Web Conf.

View full text Add to dashboard Cite

Music is an art that uses sound to convey emotions and ideas. It is a universal language that transcends cultural boundaries and can move and inspire individuals of all ages and cultures. As with every art form, the generation of music is a complex and challenging task. Despite the challenges, music generation has made considerable strides in recent years, owing to the application of artificial intelligence and machine learning. However, most research was focused on the generation of only one genre of music, i.e., classical, jazz, etc., while there are more than 40 genres of music, each with sub-genres. This paper proposes a model for multi-genre music generation using Generative Adversarial Networks (GAN). Considering symbolic music, MIDI tracks were converted into piano-roll form after the extraction of musical information. Subsequently, a GAN based model was trained to learn the distribution of training data, and it generates new data using the learned parameters. Generated music was evaluated based on a survey of musicians and professionals. The survey results validate the GAN’s ability to generate music of multiple genres.

show abstract

Section: Research Statusmentioning

confidence: 99%

Multi-Genre Symbolic Music Generation using Deep Convolutional Generative Adversarial Network

Chauhan,

Tanawala,

Hasan

2023

ITM Web Conf.

View full text Add to dashboard Cite

show abstract

“…Berbagai metode kecerdasan buatan telah digunakan untuk membangkitkan berbagai jenis musik seperti Sistem berbasis Pengetahuan, algoritme Genetika, Jaringan Saraf Tiruan (JST), termasuk metode Pembelajaran Mendalam. Metode Recurrent Neural Networks (RNN) merupakan bagian dari pembelajaran mendalam yang dapat bekerja secara efektif dalam pencarian solusi untuk permasalahan data dengan tipe time series, termasuk digunakan untuk penyelesaian masalah dalam pembangkitan musik, contohnya penelitan yang dilakukan oleh [1][2][3]. Hal ini karena beban yang diberikan lebih dekat dan tepat dengan keadaan setiap kata.…”

Section: Iunclassified

Pembangkitan Musik Klasik Menggunakan Metode Long-Short Term Memory

Amiral

Saputra

Suprayogi

et al. 2022

SINTaKS

View full text Add to dashboard Cite

Penelitian ini bertujuan untuk mengembangkan sistem otomatisasi pembangkitan musik klasik dengan menggunakan Long-Short Term Memory (LSTM), metode yang merupakan bagian dari metode Reccurent Neural Networks (RNN). Pengembangan sistem dilakukan menggunakan Bahasa pemrograman Python. Dataset dalam format MIDI yang dikumpulkan melalui situs www.piano-midi.de diolah menggunakan paket Pretty MIDI untuk mengekstrak informasi akord dan notasi dari data yang digunakan sebagai corpus. Selanjutnya, data diekstraksi untuk mendapatkan informasi nada (pitch), langkah (step) dan durasi (duration). Pelatihan jaringan LSTM menggunakan 57.887 notasi yang merupakan hasil ekstraksi data dari 14 file MIDI berisikan komposisi karya Mozart. Hasil pelatihan jaringan LSTM diukur menggunakan metode Mean Squared Error (MSE) dengan akurasi nilai loss dengan nilai loss sebesar 0,43.

show abstract

From Vision to Sound: The Application of ViT-LSTM in Music Sequence

Fang,

Zhang,

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Music Generation for Novices Using Recurrent Neural Network (RNN)

Cited by 10 publications

References 6 publications

Multi-Genre Symbolic Music Generation using Deep Convolutional Generative Adversarial Network

Multi-Genre Symbolic Music Generation using Deep Convolutional Generative Adversarial Network

Pembangkitan Musik Klasik Menggunakan Metode Long-Short Term Memory

From Vision to Sound: The Application of ViT-LSTM in Music Sequence

Contact Info

Product

Resources

About