UT-AISTimprt 提交至 ICME 2026 学术文本到音乐生成大挑战
UT-AISTimprt submission for ICME 2026 Grand Challenge on Academic Text-to-Music Generation
AI总结:
本研究针对低数据和小模型设置下的文本到音乐生成,提出基于文本或音频嵌入的聚类批量采样策略,分析模态和聚类粒度的影响,发现文本嵌入聚类在客观指标上更优,中等聚类数在客观指标最佳而大聚类数在听觉测试中结构更连贯。
摘要:
本文研究了在低数据和小模型设置下,训练文本到音频音乐生成时批量采样策略的影响。本文描述了我们对ICME 2026学术文本到音乐生成大挑战的方法和发现。训练数据使用文本嵌入或音频嵌入进行聚类,并将具有相似特征的样本分组到同一小批量中,以减轻梯度干扰。分析了模态和聚类粒度对聚类的影响。结果表明,基于文本嵌入的聚类在客观评估指标上优于基于音频嵌入的聚类。此外,不同的聚类粒度在不同评估标准下表现出不同行为:中等数量的聚类在客观指标上表现最佳,而较大数量的聚类在听觉测试中倾向于展示结构更连贯的音乐。
英文摘要:
This work investigates the effect of batch sampling strategies during training for text-to-audio music generation under low-data and small-scale model settings. This paper describes our approach and findings for the ICME 2026 Grand Challenge on Academic Text-to-Music Generation. Training data are clustered using either text embeddings or audio embeddings, and samples with similar characteristics are grouped within the same mini-batch to mitigate gradient interference. The effects of modality and cluster granularity on clustering are analyzed. Results show that clustering based on text embeddings achieves better performance on objective evaluation metrics than clustering based on audio embeddings. In addition, different cluster granularity leads to different behaviors across evaluation criteria: a moderate number of clusters performs best on objective metrics, while a larger number of clusters tends to exhibit music with more coherent structure in listening tests.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。