Leveraging Language Model Capabilities for Sound Event Detection

Abstract: LLMs reveal deep comprehension and fluent generation in the field of multi-modality. Although significant advancements have been achieved in audio multi-modality, existing methods are rarely leverage LLM for sound event detection (SED). In this work, we propose an end-to-end framework for understanding audio features while simultaneously generating sound event and their temporal location. Specifically, we employ pretrained acoustic models to capture discriminative features across different categories and LLMs for autoregressive text generation. Conventional methods generally struggle to obtain features in pure audio domain for classification. In contrast, our framework utilizes the LLM to flexibly understand abundant semantic context aligned with the acoustic representation. The experimental results showcase the effectiveness of proposed method in enhancing timestamps precision and event classification.