Leveraging Language Model Capabilities for Sound Event Detection

TL;DR

This paper introduces an end-to-end framework that combines pretrained acoustic and language models to improve sound event detection by enhancing classification accuracy and timestamp precision.

Contribution

It presents a novel approach leveraging language models for sound event detection, integrating semantic understanding with acoustic features in an end-to-end system.

Findings

Improved timestamp precision in sound event detection.

Enhanced event classification accuracy.

Effective integration of language and acoustic models.

Abstract

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.