Hierarchical Temporal Attention and Competent Teacher Network for Sound Event Detection

Sound event detection identifies specific auditory signal occurrences to recognize the sound event class and its temporal localization. While the Convolutional Recurrent Neural Network with a mean-teacher framework shows impressive SED performance, its effectiveness is hindered by its small receptive field, leading to inadequate consideration of global temporal information and imprecise event boundary localization. Moreover, existing detectors overlook the intricate interplay between temporal and frequency information, compromising detection accuracy. Simultaneously, there is an oversight in interactions between student and teacher models, leading to the teacher conveying inaccurate knowledge to the student. To solve these challenges, this paper proposes a novel robust detector named HTA-CTD, incorporating the Hierarchical Temporal Attention (HTA) and Competent Teacher Network (CTN). HTA introduces an adaptive temporal-frequency feature extraction method, while CTN minimizes reliance on strong labels. Experiments on challenging benchmarks show that our HTA-CTD outperforms the state-of-the-art detector and achieves leading performance.