EmoGen：消除情感音樂生成中的主觀偏見

EmoGen: Eliminating Subjective Bias in Emotional Music Generation

July 3, 2023

作者: Chenfei Kang, Peiling Lu, Botao Yu, Xu Tan, Wei Ye, Shikun Zhang, Jiang Bian

cs.AI

摘要

音樂被用來傳達情感，因此在自動音樂生成中生成情感音樂至關重要。先前關於情感音樂生成的研究直接使用標註的情感標籤作為控制信號，這會受到主觀偏見的影響：不同人可能會在同一音樂上標註不同的情感，而同一人在不同情境下可能會感受到不同的情感。因此，直接將情感標籤與音樂序列進行端對端的映射會混淆學習過程，並阻礙模型生成具有普遍情感的音樂。在本文中，我們提出了 EmoGen，一個情感音樂生成系統，它利用一組與情感相關的音樂屬性作為情感與音樂之間的橋樑，並將生成分為兩個階段：使用監督聚類的情感到屬性映射，以及使用自監督學習的屬性到音樂生成。這兩個階段都是有益的：在第一階段，聚類中心周圍的屬性值代表這些樣本的一般情感，有助於消除情感標籤的主觀偏見影響；在第二階段，生成完全與情感標籤解耦，因此不受主觀偏見的影響。主觀和客觀評估均顯示 EmoGen 在情感控制準確性和音樂質量方面優於先前方法，這證明了我們在生成情感音樂方面的優越性。EmoGen 生成的音樂樣本可通過此鏈接獲得：https://ai-muzic.github.io/emogen/，代碼可通過此鏈接獲得：https://github.com/microsoft/muzic/。

English

Music is used to convey emotions, and thus generating emotional music is important in automatic music generation. Previous work on emotional music generation directly uses annotated emotion labels as control signals, which suffers from subjective bias: different people may annotate different emotions on the same music, and one person may feel different emotions under different situations. Therefore, directly mapping emotion labels to music sequences in an end-to-end way would confuse the learning process and hinder the model from generating music with general emotions. In this paper, we propose EmoGen, an emotional music generation system that leverages a set of emotion-related music attributes as the bridge between emotion and music, and divides the generation into two stages: emotion-to-attribute mapping with supervised clustering, and attribute-to-music generation with self-supervised learning. Both stages are beneficial: in the first stage, the attribute values around the clustering center represent the general emotions of these samples, which help eliminate the impacts of the subjective bias of emotion labels; in the second stage, the generation is completely disentangled from emotion labels and thus free from the subjective bias. Both subjective and objective evaluations show that EmoGen outperforms previous methods on emotion control accuracy and music quality respectively, which demonstrate our superiority in generating emotional music. Music samples generated by EmoGen are available via this link:https://ai-muzic.github.io/emogen/, and the code is available at this link:https://github.com/microsoft/muzic/.