Adaptive Few-Shot Learning Algorithm for Rare Sound Event Detection

Abstract

Sound event detection is to infer the event by understanding the surrounding environmental sounds. Due to the scarcity of rare sound events, it becomes challenging for the well-trained detectors which have learned too much prior knowledge. Meanwhile, few-shot learning methods promise a good generalization ability when facing a new limited-data task. Recent approaches have achieved promising results in this field. However, these approaches treat each support example independently, ignoring the information of other examples from the whole task. Because of this, most of previous methods are constrained to generate a same feature embedding for all test-time tasks, which is not adaptive to each inputted data. In this work, we propose a novel task-adaptive module which is easy to plant into any metric-based few-shot learning frameworks. The module could identify the task-relevant feature dimension. Incorporating our module improves the performance considerably on two datasets over baseline methods, especially for the transductive propagation network. Such as +6.8% for 5-way 1-shot accuracy on ESC-50, and +5.9% on noiseESC-50. We investigate our approach in the domain-mismatch setting and also achieve better results than previous methods.

A Systematic Review of Rare Events Detection Across Modalities using Machine Learning and Deep Learning

“…The introduction of an adaptive few-shot learning algorithm for rare sound event detection aimed to improve few-shot learning in sound-event recognition [53]. This algorithm identifies rare auditory events with limited information, which is a common issue in practical situations.…”

“…In [53], metric-based few-shot learning with a taskadaptive module was used to detect rare sound events by identifying class uniqueness and support set commonality.…”

A Systematic Review of Rare Events Detection Across Modalities using Machine Learning and Deep Learning

“…Sounds are auditory sensations created by vibrations that travel through a medium, such as air, and are perceived by our ears. The automatic detection of environmental sound events has recently gained attention [53]. Unlike speech and music, environmental sounds lack stationary patterns.…”

“…Spectrogram computation and features extraction methods (e.g., MFCCs or log-mel spectrograms) are commonly used in sound event detection [53]. In [62], Mel log energy (MLE) features are derived using the fast Fourier transform (FFT) to discern distinct frequencies in an audio signal.…”

HalluAudio: Hallucinating Frequency as Concepts for Few-Shot Audio Classification

“…Beyond that, a very limited number of works tried to develop new methods for few-shot audio classification. For example, [14] proposed an attentional GNN for audio classification, [15] developed an attention similarity module and [16] integrated CTM [17], TPN [8] and MixUp [18] with audio data augmentation to build a task-adaptive module. Nonetheless, all these methods are still focusing only on the extracted unstructured embedding space rather than the audio spectrogram itself, just like the most common way for few-shot image classification.…”