计算机科学
强化学习
旋律
即兴创作
人工智能
和声(音乐)
复调
背景(考古学)
机器学习
语音识别
音乐剧
心理学
艺术
教育学
古生物学
视觉艺术
生物
作者
Nan Jiang,Sheng Jin,Zhiyao Duan,Changshui Zhang
标识
DOI:10.48550/arxiv.2002.03082
摘要
This paper presents a deep reinforcement learning algorithm for online accompaniment generation, with potential for real-time interactive human-machine duet improvisation. Different from offline music generation and harmonization, online music accompaniment requires the algorithm to respond to human input and generate the machine counterpart in a sequential order. We cast this as a reinforcement learning problem, where the generation agent learns a policy to generate a musical note (action) based on previously generated context (state). The key of this algorithm is the well-functioning reward model. Instead of defining it using music composition rules, we learn this model from monophonic and polyphonic training data. This model considers the compatibility of the machine-generated note with both the machine-generated context and the human-generated context. Experiments show that this algorithm is able to respond to the human part and generate a melodic, harmonic and diverse machine part. Subjective evaluations on preferences show that the proposed algorithm generates music pieces of higher quality than the baseline method.
科研通智能强力驱动
Strongly Powered by AbleSci AI