Enhancing Music Generation With a Semantic-Based Sequence-to-Music Transformer Framework

Author:

Xu Yang1

Affiliation:

1. Conservatory of Music, Shangqiu Normal University, China

Abstract

Music generation became a platform for creative expression, promoting artistic innovation, personalized experiences, and cultural integration, with implications for education and creative industry development. But generating music that resonates emotionally is a challenge. Therefore, we introduce a new framework called the Sequence-to-Music Transformer Framework for Music Generation. This framework employs a simple encoder-decoder Transformer to model music by transforming its fundamental notes into a sequence of discrete tokens. The model learns to generate this sequence token by token. The encoder extracts melodic features of the music, while the decoder uses these extracted features to generate the music sequence. Generation is performed in an auto-regressive manner, meaning the model generates tokens based on previously observed tokens. Music melodic features are integrated into the decoder through cross-attention layers, and the generation process concludes when “end” is generated. The experimental results achieve state-of-the-art performance on a wide range of datasets.

Publisher

IGI Global

Reference44 articles.

1. Detection of Bryde's whale short pulse calls using time domain features with hidden Markov models

2. A Context-Independent Ontological Linked Data Alignment Approach to Instance Matching

3. Geometric Deep Learning: Going beyond Euclidean data

4. Multidirectional Gradient Feature With Shape Index for Effective Texture Classification

5. Choi, K., Hawthorne, C., Simon, I., Dinculescu, M., & Engel, J. (2020). Encoding musical style with transformer autoencoders. In Proceedings of the 37th International Conference on Machine Learning, 119, 1899–1908. MLResearch Press. https://proceedings.mlr.press/v119/choi20b.html

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3