Leveraging Language Model Capabilities for Sound Event Detection
This work addresses sound event detection, a domain-specific problem in audio processing, by integrating language models, representing a novel method for a known bottleneck.
The authors tackled sound event detection by proposing an end-to-end framework that leverages language models to understand audio features and generate sound events with temporal locations, resulting in enhanced timestamp precision and event classification.
Large language models 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 language model 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 language models for autoregressive text generation. Conventional methods generally struggle to obtain features in pure audio domain for classification. In contrast, our framework utilizes the language model 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.