Text Prompt is Not Enough: Sound Event Enhanced Prompt Adapter for Target Style Audio Generation
This addresses the limitation of text-only prompts in capturing nuanced audio styles for audio generation tasks, offering an incremental improvement over existing methods.
The paper tackles the problem of multi-style audio generation by proposing a Sound Event Enhanced Prompt Adapter that uses text and audio references for adaptive style control, achieving state-of-the-art results with a Fréchet Distance of 26.94 and KL Divergence of 1.82.
Current mainstream audio generation methods primarily rely on simple text prompts, often failing to capture the nuanced details necessary for multi-style audio generation. To address this limitation, the Sound Event Enhanced Prompt Adapter is proposed. Unlike traditional static global style transfer, this method extracts style embedding through cross-attention between text and reference audio for adaptive style control. Adaptive layer normalization is then utilized to enhance the model's capacity to express multiple styles. Additionally, the Sound Event Reference Style Transfer Dataset (SERST) is introduced for the proposed target style audio generation task, enabling dual-prompt audio generation using both text and audio references. Experimental results demonstrate the robustness of the model, achieving state-of-the-art Fréchet Distance of 26.94 and KL Divergence of 1.82, surpassing Tango, AudioLDM, and AudioGen. Furthermore, the generated audio shows high similarity to its corresponding audio reference. The demo, code, and dataset are publicly available.