This report presents the technical details of our submission to the 2023 Epic-Kitchen EPIC-SOUNDS Audio-Based Interaction Recognition Challenge. The task is to learn the mapping from audio samples to their corresponding action labels. To achieve this goal, we propose a simple yet effective single-stream CNN-based architecture called AudioInceptionNeXt that operates on the time-frequency log-mel-spectrogram of the audio samples. Motivated by the design of the InceptionNeXt, we propose parallel multi-scale depthwise separable convolutional kernels in the AudioInceptionNeXt block, which enable the model to learn the time and frequency information more effectively. The large-scale separable kernels capture the long duration of activities and the global frequency semantic information, while the small-scale separable kernels capture the short duration of activities and local details of frequency information. Our approach achieved 55.43% of top-1 accuracy on the challenge test set, ranked as 1st on the public leaderboard. Codes are available anonymously at https://github.com/StevenLauHKHK/AudioInceptionNeXt.git.

翻译：本报告详细介绍了我们参加2023年Epic-Kitchen EPIC-SOUNDS基于音频的交互识别挑战赛的技术方案。该任务旨在学习从音频样本到对应动作标签的映射。为实现这一目标，我们提出了一种简单而高效的基于单流CNN的架构，称为AudioInceptionNeXt，该架构直接对音频样本的时频对数梅尔频谱图进行处理。受InceptionNeXt设计的启发，我们在AudioInceptionNeXt模块中引入了并行的多尺度深度可分离卷积核，使模型能够更有效地学习时间和频率信息。大尺度可分离卷积核用于捕获活动的长时间跨度及全局频率语义信息，而小尺度可分离卷积核则负责捕获短期活动及频率信息的局部细节。我们的方法在挑战测试集上取得了55.43%的top-1准确率，位列公开排行榜第一名。代码可匿名访问https://github.com/StevenLauHKHK/AudioInceptionNeXt.git获取。