Attention-Based Joint Training of Noise Suppression and Sound Event Detection for Noise-Robust Classification

Abstract

Sound event detection (SED) recognizes the corresponding sound event of an incoming signal and estimates its temporal boundary. Although SED has been recently developed and used in various fields, achieving noise-robust SED in a real environment is typically challenging owing to the performance degradation due to ambient noise. In this paper, we propose combining a pretrained time-domain speech-separation-based noise suppression network (NS) and a pretrained classification network to improve the SED performance in real noisy environments. We use group communication with a context codec method (GC3)-equipped temporal convolutional network (TCN) for the noise suppression model and a convolutional recurrent neural network for the SED model. The former significantly reduce the model complexity while maintaining the same TCN module and performance as a fully convolutional time-domain audio separation network (Conv-TasNet). We also do not update the weights of some layers (i.e., freeze) in the joint fine-tuning process and add an attention module in the SED model to further improve the performance and prevent overfitting. We evaluate our proposed method using both simulation and real recorded datasets. The experimental results show that our method improves the classification performance in a noisy environment under various signal-to-noise-ratio conditions.

Adaptive Noise Reduction Algorithm Based on SPP and NMF for Environmental Sound Event Recognition under Low-SNR Conditions

“…The recognition of environmental sound (ES) enables the monitoring of certain specific event, since ES have the potential of characterizing the surrounding environment. However, one key factor that affects detection and classification performance is the diverse and unpredictable interference noise in the real-life scenarios [1]. Therefore, noise reduction (NR), as a part of the preprocessing of ES, has important application prospects in human-computer interaction [2], animal behavior monitoring [3], anomalous sounds for machine condition monitoring [4], and domestic risk scenarios [5].…”